INDEX

Explanations

details related to incidents

oai_token-act-pair · gpt-3.5-turbo

instances of significant events or actions

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

-)

-0.70

onom

-0.66

ãĤ§

-0.64

 favourites

-0.63

;)

-0.62

 proverb

-0.61

iri

-0.61

 quir

-0.58

)-

-0.58

)</

-0.58

POSITIVE LOGITS

igslist

0.67

htaking

0.65

aundering

0.64

 respectively

0.63

osher

0.63

selage

0.62

tackle

0.62

oples

0.62

emetery

0.60

lycer

0.60

Activations Density 1.304%

details related to incidents

instances of significant events or actions

No Comments

No Known Activations