INDEX

Explanations

adjectives conveying extreme intensity or importance

oai_token-act-pair · gpt-3.5-turbo

descriptors conveying high levels of intensity or significance

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

mun

-0.76

checked

-0.72

adier

-0.72

thur

-0.71

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.69

SY

-0.69

amb

-0.68

MED

-0.68

Jer

-0.67

rahim

-0.67

POSITIVE LOGITS

 imaginable

1.06

 manifestation

1.02

 thing

0.96

 aspects

0.95

 aspect

0.92

 manifestations

0.86

 ever

0.85

 incarnation

0.85

 conceivable

0.84

 exponent

0.82

Activations Density 0.107%

adjectives conveying extreme intensity or importance

descriptors conveying high levels of intensity or significance

No Comments

No Known Activations