INDEX

Explanations

phrases related to a specific quest or mission

oai_token-act-pair · gpt-3.5-turbo

the word "quest" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

weights

-0.66

paces

-0.64

bestos

-0.63

 slices

-0.62

oci

-0.61

creen

-0.59

waves

-0.59

 layers

-0.57

AW

-0.56

 sexes

-0.56

POSITIVE LOGITS

ioned

1.54

naire

1.29

naires

1.09

love

0.99

rade

0.94

ogue

0.81

shire

0.79

aire

0.79

finding

0.78

lon

0.76

Activations Density 0.015%

phrases related to a specific quest or mission

the word "quest" and its variations

No Comments

No Known Activations