INDEX

Explanations

phrases related to the name "Cap"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Cap" and its variations or context

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ĪĴ

-0.86

hower

-0.84

Reloaded

-0.82

ãģį

-0.75

WAYS

-0.74

 silence

-0.74

perse

-0.72

ĸļ

-0.70

td

-0.67

 else

-0.63

POSITIVE LOGITS

itals

1.13

Cap

1.13

itol

1.12

Cap

1.00

illus

0.95

illary

0.94

abulary

0.93

aldi

0.93

acity

0.93

cap

0.92

Activations Density 0.004%

phrases related to the name "Cap"

mentions of the name "Cap" and its variations or context

No Known Activations