INDEX

Explanations

word stems or partial words with varying accents or special characters

oai_token-act-pair · gpt-3.5-turbo

special characters and non-typical letter combinations, indicating a focus on unique or unusual textual elements

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é»Ĵ

-0.85

ongyang

-0.78

ccording

-0.75

#$#$

-0.71

 WATCHED

-0.70

ecause

-0.68

eworthy

-0.67

xtap

-0.66

é£

-0.65

 Unloaded

-0.63

POSITIVE LOGITS

enment

1.01

 coli

0.71

enko

0.67

hyde

0.66

 Valencia

0.65

 Choi

0.63

cheon

0.63

ciating

0.63

oyer

0.62

 Rangers

0.61

Activations Density 0.462%

word stems or partial words with varying accents or special characters

special characters and non-typical letter combinations, indicating a focus on unique or unusual textual elements

No Comments

No Known Activations