INDEX

Explanations

statements related to accepting or taking responsibility

oai_token-act-pair · gpt-3.5-turbo

references to personal or collective responsibility

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ugen

-0.76

vae

-0.73

wikipedia

-0.70

corn

-0.70

tering

-0.69

ropolis

-0.68

quart

-0.66

TERN

-0.64

ergy

-0.64

inton

-0.63

POSITIVE LOGITS

 responsibility

1.00

 responsibilities

0.96

 delegated

0.87

lessness

0.85

 owed

0.82

 culp

0.81

ignty

0.79

 Responsibility

0.79

 responsibly

0.77

lessly

0.74

Activations Density 0.031%

statements related to accepting or taking responsibility

references to personal or collective responsibility

No Comments

No Known Activations