INDEX

Explanations

phrases or sentences indicating a reason or justification

oai_token-act-pair · gpt-3.5-turbo

instances of the word "because" indicating reasoning or justification

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

wn

-0.72

jet

-0.70

pmwiki

-0.68

alysed

-0.67

iets

-0.66

whel

-0.64

ax

-0.64

 exting

-0.64

ns

-0.64

moderate

-0.64

POSITIVE LOGITS

 otherwise

1.05

 unlike

0.95

hey

0.94

 nobody

0.91

 there

0.91

 frankly

0.89

it

0.88

 they

0.88

 obviously

0.88

we

0.85

Activations Density 0.093%

phrases or sentences indicating a reason or justification

instances of the word "because" indicating reasoning or justification

No Comments

No Known Activations