INDEX

Explanations

adjectives related to strength or power

oai_token-act-pair · gpt-3.5-turbo

instances of the word "mighty"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

APD

-0.81

getting

-0.80

Interstitial

-0.79

*/(

-0.77

cius

-0.76

skirts

-0.74

both

-0.73

ETF

-0.73

ople

-0.73

instein

-0.73

POSITIVE LOGITS

 Mighty

1.00

 mighty

0.88

 Hercules

0.76

 heavyweight

0.75

 merry

0.74

ighty

0.74

 earthqu

0.74

 beast

0.73

 bulls

0.71

 prick

0.69

Activations Density 0.014%

adjectives related to strength or power

instances of the word "mighty"

No Comments

No Known Activations