INDEX

Explanations

words related to the concept of neutrality

oai_token-act-pair · gpt-3.5-turbo

phrases and concepts associated with neutrality

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

Hop

-0.86

Mill

-0.85

BOOK

-0.79

soDeliveryDate

-0.78

URE

-0.78

URES

-0.76

Amazing

-0.76

MAT

-0.76

RESULTS

-0.74

MA

-0.74

POSITIVE LOGITS

 neutral

1.00

izes

1.00

utral

0.97

izing

0.96

izers

0.93

ization

0.92

 neutrality

0.89

izer

0.86

 buoy

0.83

ize

0.83

Activations Density 0.007%

words related to the concept of neutrality

phrases and concepts associated with neutrality

No Comments

No Known Activations