INDEX

Explanations

adjectives denoting a level of intensity or extremity

oai_token-act-pair · gpt-3.5-turbo

terms related to "mild" qualities or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

alyst

-0.65

andise

-0.61

 Kirin

-0.61

ourced

-0.61

hedral

-0.61

 Horizon

-0.61

Yue

-0.60

thia

-0.57

 Chung

-0.57

tical

-0.56

POSITIVE LOGITS

ew

1.12

er

0.96

atures

0.87

enstein

0.85

erers

0.83

ering

0.79

hello

0.77

ered

0.76

reth

0.72

ers

0.70

Activations Density 0.052%

adjectives denoting a level of intensity or extremity

terms related to "mild" qualities or conditions

No Comments

No Known Activations