INDEX

Explanations

words related to negative emotions and consequences

oai_token-act-pair · gpt-3.5-turbo

suffixes indicating negative sentiments or conditions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inav

-0.78

herty

-0.76

sav

-0.72

ergy

-0.71

oret

-0.71

ITNESS

-0.68

vez

-0.67

ENN

-0.67

gres

-0.66

ellar

-0.65

POSITIVE LOGITS

ously

0.80

 inflicted

0.75

 thereof

0.72

 Bastard

0.70

 plag

0.70

 perpetrated

0.70

quo

0.69

uous

0.69

OUS

0.69

naires

0.66

Activations Density 0.270%

words related to negative emotions and consequences

suffixes indicating negative sentiments or conditions

No Comments

No Known Activations