INDEX

Explanations

formulas, conditions, or scenarios related to science or experimental subjects

oai_token-act-pair · gpt-3.5-turbo

parenthetical phrases or expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 dangerously

-0.77

 heavily

-0.74

 completely

-0.73

 glare

-0.73

 retard

-0.71

 baffled

-0.71

 whip

-0.71

 firmly

-0.71

 bows

-0.71

 awfully

-0.70

POSITIVE LOGITS

see

1.65

including

1.64

such

1.62

excluding

1.55

typically

1.54

except

1.52

usually

1.50

Figure

1.50

often

1.47

especially

1.46

Activations Density 0.157%

formulas, conditions, or scenarios related to science or experimental subjects

parenthetical phrases or expressions

No Comments

No Known Activations