INDEX

Explanations

words related to shopping or physical retail locations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "hop" and its variations

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

Downloadha

-0.88

 behold

-0.74

anguage

-0.71

 herein

-0.68

 bruising

-0.68

 Monstrous

-0.68

 Dynamics

-0.66

 withd

-0.63

etheless

-0.62

$$$$

-0.61

POSITIVE LOGITS

efully

1.58

eful

1.50

eless

1.17

hop

1.06

Hop

1.00

esy

0.98

daq

0.93

rak

0.88

achu

0.88

Hop

0.87

Activations Density 0.015%

words related to shopping or physical retail locations

occurrences of the word "hop" and its variations

No Comments

No Known Activations