INDEX

Explanations

phrases related to news events, incidents, and places

oai_token-act-pair · gpt-3.5-turbo

instances of account breaches or hacking incidents

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

ificant

-0.54

quartered

-0.49

 consists

-0.48

versions

-0.48

 Thumbnails

-0.46

reek

-0.45

 Accessed

-0.44

odcast

-0.43

 START

-0.43

particularly

-0.43

POSITIVE LOGITS

)).

0.69

$.

0.68

?".

0.57

!.

0.54

}.

0.54

).

0.53

Ń·

0.52

itte

0.52

igslist

0.52

".

0.51

Activations Density 1.861%

phrases related to news events, incidents, and places

instances of account breaches or hacking incidents

No Comments

No Known Activations