INDEX

Explanations

statements made by official authorities

oai_token-act-pair · gpt-3.5-turbo

references to government or administrative officials

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

ï¸

-0.77

 Horses

-0.75

rums

-0.73

esville

-0.70

effects

-0.66

ĸļ

-0.66

ocene

-0.66

bows

-0.63

vasive

-0.63

Spect

-0.62

POSITIVE LOGITS

dom

1.01

ially

0.87

doms

0.83

 tasked

0.83

 overseeing

0.78

 sanctioned

0.75

 stationed

0.73

ials

0.71

itarian

0.71

ulty

0.70

Activations Density 0.032%

statements made by official authorities

references to government or administrative officials

No Comments

No Known Activations