INDEX

Explanations

phrases related to small or minor details

oai_token-act-pair · gpt-3.5-turbo

references to small details or insignificant elements 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Roses

-0.75

 Skies

-0.72

åĭ

-0.71

ukong

-0.66

Bridge

-0.65

ayn

-0.64

andise

-0.64

etheus

-0.63

ready

-0.63

 Gleaming

-0.63

POSITIVE LOGITS

(<

1.35

 insignificant

0.98

tiny

0.95

(~

0.93

 scattered

0.89

 sized

0.88

 increments

0.86

 incremental

0.84

 tucked

0.81

 manageable

0.81

Activations Density 0.265%

phrases related to small or minor details

references to small details or insignificant elements in various contexts

No Comments

No Known Activations