INDEX

Explanations

proper nouns related to individuals

oai_token-act-pair · gpt-3.5-turbo

the repeated occurrence of the token "ek" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 exha

-0.69

ACTED

-0.69

 contrace

-0.68

saf

-0.66

 cort

-0.65

inals

-0.65

 Spray

-0.64

 redistributed

-0.61

 avalanche

-0.60

 handc

-0.60

POSITIVE LOGITS

nown

1.19

ek

1.07

kers

0.94

eks

0.94

eker

0.94

kies

0.91

owitz

0.91

ilon

0.89

ules

0.89

enstein

0.88

Activations Density 0.010%

proper nouns related to individuals

the repeated occurrence of the token "ek" in various contexts

No Comments

No Known Activations