INDEX

Explanations

references to things that are preferred or enjoyed by an individual

oai_token-act-pair · gpt-3.5-turbo

references to favorite or preferred items, activities, or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

aping

-0.92

aton

-0.87

ldon

-0.80

attle

-0.80

redits

-0.79

heed

-0.79

ural

-0.76

hare

-0.76

avis

-0.76

idem

-0.75

POSITIVE LOGITS

Favorite

0.91

 pokemon

0.89

 tricks

0.83

 hobbies

0.82

 hobby

0.80

 unsolved

0.79

 favorite

0.79

 haunt

0.77

 moments

0.77

 brands

0.77

Activations Density 0.037%

references to things that are preferred or enjoyed by an individual

references to favorite or preferred items, activities, or experiences

No Comments

No Known Activations