INDEX

Explanations

references to specific numbers or figures

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

books

-0.78

ulhu

-0.75

Britain

-0.71

Scotland

-0.68

Brexit

-0.68

Muslims

-0.67

aneers

-0.66

Frameworks

-0.66

Jews

-0.65

adoes

-0.64

POSITIVE LOGITS

 latter

1.52

 aforementioned

1.29

 foregoing

1.17

 discrepancy

1.11

 same

1.05

 afore

1.02

 difference

0.96

 remainder

0.96

 above

0.95

 disparity

0.93

Activations Density 0.542%

references to specific numbers or figures

occurrences of the word "the" in various contexts

No Comments

No Known Activations