INDEX

Explanations

years mentioned within statements

oai_token-act-pair · gpt-3.5-turbo

references to significant historical events or milestones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 voic

-0.69

ften

-0.65

eln

-0.61

 upcoming

-0.60

 forthcoming

-0.59

Fax

-0.59

 knots

-0.59

oret

-0.57

ãĤĬ

-0.57

UGC

-0.57

POSITIVE LOGITS

 inception

0.91

nas

0.64

Era

0.61

 VIDEOS

0.61

@#&

0.60

era

0.59

allows

0.59

 Coll

0.57

ties

0.57

 millennium

0.57

Activations Density 0.334%

years mentioned within statements

references to significant historical events or milestones

No Comments

No Known Activations