INDEX

Explanations

words related to positive and negative experiences or events

oai_token-act-pair · gpt-3.5-turbo

statements about positive and negative experiences or outcomes

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

EVA

-0.73

Footnote

-0.72

Ø¨

-0.71

Britain

-0.70

Pub

-0.66

Øª

-0.66

 Portuguese

-0.65

 Geneva

-0.64

Ùĩ

-0.63

ART

-0.63

POSITIVE LOGITS

ourced

1.03

aic

1.02

ided

1.01

ides

0.98

cale

0.96

undown

0.95

sembly

0.95

icum

0.93

ourcing

0.93

ugar

0.92

Activations Density 0.023%

words related to positive and negative experiences or events

statements about positive and negative experiences or outcomes

No Comments

No Known Activations