INDEX

Explanations

dates or time-related information

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in."

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

âĿ

-0.67

}}

-0.65

Newsletter

-0.64

 Defenders

-0.62

²¾

-0.61

 Trends

-0.58

ŀ

-0.58

Ľ

-0.58

bugs

-0.57

Ħ¢

-0.56

POSITIVE LOGITS

elling

0.78

cause

0.77

bill

0.77

ardless

0.71

lining

0.70

cluding

0.68

bda

0.67

 whom

0.65

lighting

0.64

 boarding

0.64

Activations Density 0.321%

dates or time-related information

occurrences of the word "in."

No Comments

No Known Activations