INDEX

Explanations

names or terms related to specifically 'Bowerman'

oai_token-act-pair · gpt-3.5-turbo

words related to individuals with the surname "Bower."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ravel

-0.66

âĸ¬âĸ¬

-0.65

ocular

-0.64

odor

-0.59

 distinguishing

-0.59

ADRA

-0.59

 Takeru

-0.57

 earth

-0.57

ROM

-0.57

 mism

-0.56

POSITIVE LOGITS

ower

1.13

sonian

0.94

owers

0.91

izont

0.86

loo

0.84

sburg

0.82

atives

0.81

ing

0.79

lein

0.76

houses

0.76

Activations Density 0.010%

names or terms related to specifically 'Bowerman'

words related to individuals with the surname "Bower."

No Comments

No Known Activations