INDEX

Explanations

phrases indicating inclusion or conjunction, such as "both" and "and"

oai_token-act-pair · gpt-3.5-turbo

conjunctions and patterns of paired relationships or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

oops

-0.79

Reviewed

-0.77

odore

-0.75

uel

-0.73

ãĤ¨

-0.71

ventus

-0.70

raq

-0.70

notations

-0.69

eks

-0.69

noon

-0.69

POSITIVE LOGITS

 ours

0.96

 theirs

0.79

 hers

0.78

 outright

0.77

 yours

0.75

 nons

0.75

nam

0.73

 actual

0.72

 otherwise

0.71

 nonex

0.68

Activations Density 0.117%

phrases indicating inclusion or conjunction, such as "both" and "and"

conjunctions and patterns of paired relationships or comparisons

No Comments

No Known Activations