INDEX

Explanations

instances of family dynamics, particularly parents and number of children

oai_token-act-pair · gpt-3.5-turbo

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olid

-0.71

nexus

-0.71

Ĥİ

-0.70

ioxide

-0.69

nels

-0.65

issions

-0.65

NRS

-0.64

HUD

-0.64

krit

-0.63

DIT

-0.62

POSITIVE LOGITS

thood

0.81

 twins

0.78

 pearl

0.76

pins

0.73

 daughters

0.73

 bride

0.69

 children

0.68

 Frankenstein

0.68

 Stella

0.68

 daughter

0.67

Activations Density 0.052%

instances of family dynamics, particularly parents and number of children

No Comments

No Known Activations