INDEX

Explanations

words related to cold weather or icy conditions

oai_token-act-pair · gpt-3.5-turbo

mentions of "Frost" and related terms, particularly in contexts suggesting cold or icy conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

>>>>>>>>

-0.68

 Indones

-0.66

Columb

-0.64

Attempts

-0.64

selves

-0.64

 Hispan

-0.64

ENTION

-0.63

ulhu

-0.62

ister

-0.62

Brazil

-0.62

POSITIVE LOGITS

bite

1.26

enstein

0.94

burn

0.94

flake

0.91

wolves

0.90

fall

0.90

iness

0.89

 Frost

0.88

fur

0.85

bolt

0.81

Activations Density 0.009%

words related to cold weather or icy conditions

mentions of "Frost" and related terms, particularly in contexts suggesting cold or icy conditions

No Comments

No Known Activations