INDEX

Explanations

instances of neglect or negligence in various contexts

oai_token-act-pair · gpt-3.5-turbo

terms associated with neglect and negligence

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

Rated

-0.64

CHAT

-0.63

 unden

-0.63

SW

-0.62

 injunction

-0.62

ernels

-0.61

soType

-0.61

 VIDE

-0.61

 Rite

-0.61

Streamer

-0.60

POSITIVE LOGITS

ful

0.97

fully

0.82

icit

0.82

mental

0.80

fulness

0.79

ive

0.78

luster

0.76

shire

0.75

reatment

0.75

lessly

0.74

Activations Density 0.052%

instances of neglect or negligence in various contexts

terms associated with neglect and negligence

No Comments

No Known Activations