INDEX

Explanations

pairs of related items or concepts (commonly expressed with both X and Y)

oai_token-act-pair · gpt-3.5-turbo

the word "both" indicating comparisons or dualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uel

-0.88

xit

-0.79

xus

-0.75

regate

-0.75

hess

-0.73

enium

-0.71

ves

-0.71

erto

-0.70

ugu

-0.69

zag

-0.69

POSITIVE LOGITS

 sexes

1.21

 genders

1.07

 sides

0.91

 livest

0.88

 halves

0.77

 domestically

0.75

theless

0.75

 offensively

0.74

 individually

0.69

 anecd

0.68

Activations Density 0.035%

pairs of related items or concepts (commonly expressed with both X and Y)

the word "both" indicating comparisons or dualities

No Comments

No Known Activations