INDEX

Explanations

comparisons of quantity between different scenarios

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate cause and effect relationships

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anka

-0.72

osate

-0.61

laim

-0.57

usp

-0.57

alach

-0.55

Origin

-0.55

stros

-0.54

iasco

-0.54

bara

-0.54

ossus

-0.54

POSITIVE LOGITS

 fewer

1.75

 less

1.59

 clearer

1.54

 nicer

1.53

 quicker

1.52

 sharper

1.50

 richer

1.49

 shorter

1.47

 easier

1.46

 smoother

1.46

Activations Density 0.895%

comparisons of quantity between different scenarios

phrases that indicate cause and effect relationships

No Comments

No Known Activations