INDEX

Explanations

words related to automatic items or devices

oai_token-act-pair · gpt-3.5-turbo

references to automatic mechanisms or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

borough

-0.99

ĸļ

-0.95

ä»£

-0.79

apest

-0.77

boro

-0.75

gdala

-0.75

nard

-0.74

usky

-0.73

our

-0.73

=-=-=-=-

-0.72

POSITIVE LOGITS

 transmission

1.28

 transmissions

1.00

 braking

0.96

omatic

0.92

 renewal

0.89

 conversion

0.89

 captcha

0.85

 induction

0.85

ity

0.85

 termination

0.81

Activations Density 0.026%

words related to automatic items or devices

references to automatic mechanisms or systems

No Comments

No Known Activations