INDEX

Explanations

adjectives followed by numbers indicating a level or rank

oai_token-act-pair · gpt-3.5-turbo

words related to capability or potential

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

erva

-0.89

avorite

-0.88

krit

-0.86

herry

-0.81

itect

-0.78

ilitary

-0.77

urer

-0.77

ynski

-0.77

ricting

-0.74

escription

-0.73

POSITIVE LOGITS

 Danger

0.83

 Haram

0.79

 Squirrel

0.78

 Crim

0.77

pedia

0.74

 Puzzles

0.72

 Rash

0.72

Moe

0.70

 Isles

0.69

 Cous

0.68

Activations Density 0.024%

adjectives followed by numbers indicating a level or rank

words related to capability or potential

No Comments

No Known Activations