INDEX

Explanations

references to publications, news sources, and dates

oai_token-act-pair · gpt-3.5-turbo

the presence of vertical bar characters in the text

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

rons

-0.83

ifts

-0.83

anski

-0.78

ippi

-0.78

orical

-0.77

anium

-0.77

ifting

-0.77

ory

-0.77

enance

-0.76

raints

-0.75

POSITIVE LOGITS

cffff

1.02

|--

0.93

Â·Â·

0.83

âĢ¢âĢ¢

0.73

thel

0.72

 +---

0.71

cffffcc

0.71

 Posted

0.70

////////////////////////////////

0.68

————

0.68

Activations Density 0.015%

references to publications, news sources, and dates

the presence of vertical bar characters in the text

No Comments

No Known Activations