INDEX

Explanations

adjectives related to gentleness

oai_token-act-pair · gpt-3.5-turbo

variations of the word "gentle."

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

aucus

-0.83

etheus

-0.80

uments

-0.73

ulhu

-0.73

halla

-0.71

anooga

-0.71

aepernick

-0.70

eters

-0.70

 Gutenberg

-0.69

ilater

-0.69

POSITIVE LOGITS

 breeze

1.09

 gentle

0.97

maid

0.88

 slope

0.84

 bree

0.84

 tranquil

0.82

nud

0.82

tip

0.78

atures

0.76

 lull

0.75

Activations Density 0.037%

adjectives related to gentleness

variations of the word "gentle."

No Comments

No Known Activations