INDEX

Explanations

stylistic descriptions or characteristics

oai_token-act-pair · gpt-3.5-turbo

references to styles or forms of expression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ĪĴ

-0.86

-0.81

conservancy

-0.75

 sacrific

-0.70

ESA

-0.70

Christ

-0.68

quished

-0.67

eneg

-0.67

CU

-0.67

 Contributions

-0.66

POSITIVE LOGITS

lishes

0.80

ulation

0.70

 mock

0.63

 urge

0.62

 urges

0.61

 unintentionally

0.60

 style

0.59

beh

0.59

 digest

0.59

 Breach

0.59

Activations Density 0.000%

stylistic descriptions or characteristics

references to styles or forms of expression

No Comments

No Known Activations