INDEX

Explanations

phrases indicating uncertainty or questioning

oai_token-act-pair · gpt-3.5-turbo

references to location or direction

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

İĭ

-0.67

ANN

-0.66

 Hacker

-0.63

 Architects

-0.61

 âĹı

-0.61

 Leilan

-0.60

 Fargo

-0.59

 RELE

-0.59

BP

-0.59

aki

-0.58

POSITIVE LOGITS

abouts

0.81

 nearest

0.73

Interstitial

0.73

ilater

0.69

eneg

0.69

 intersect

0.67

coe

0.66

 weakest

0.65

ezvous

0.65

lins

0.64

Activations Density 0.298%

phrases indicating uncertainty or questioning

references to location or direction

No Comments

No Known Activations