INDEX

Explanations

phrases related to military or armed forces

oai_token-act-pair · gpt-3.5-turbo

references to specific people and events

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

 whilst

-0.76

Firstly

-0.66

 independ

-0.63

 cunt

-0.61

!".

-0.61

ie

-0.60

 Whilst

-0.60

gement

-0.58

 ****

-0.58

 english

-0.58

POSITIVE LOGITS

 POLITICO

0.70

 Canaver

0.69

 Fiorina

0.68

 Goodell

0.65

 HuffPost

0.64

 Cohn

0.61

 DeVos

0.61

 longtime

0.60

 GOODMAN

0.60

 nonprofits

0.59

Activations Density 2.033%

phrases related to military or armed forces

references to specific people and events

No Comments

No Known Activations