INDEX

Explanations

adjectives describing unsettling or disturbing characteristics

oai_token-act-pair · gpt-3.5-turbo

words that describe something as creepy or associated with creepiness

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

shire

-0.92

ership

-0.86

inen

-0.86

mental

-0.85

ribut

-0.82

aire

-0.80

hip

-0.80

lete

-0.80

âĢ¢âĢ¢âĢ¢âĢ¢

-0.80

iche

-0.78

POSITIVE LOGITS

 stuff

0.84

 sounding

0.79

fun

0.78

 looking

0.76

 shit

0.76

tid

0.75

 Guys

0.74

 enough

0.74

 darn

0.74

 little

0.73

Activations Density 0.040%

adjectives describing unsettling or disturbing characteristics

words that describe something as creepy or associated with creepiness

No Comments

No Known Activations