INDEX

Explanations

the article "a"

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

INGTON

-0.79

Edit

-0.79

 presently

-0.76

eston

-0.70

hello

-0.69

Therefore

-0.69

enery

-0.68

 âĢº

-0.66

 hereby

-0.66

Entity

-0.66

POSITIVE LOGITS

 mistake

1.04

 revelation

1.01

 pivotal

0.97

 surprise

0.96

 precursor

0.96

 breakthrough

0.94

 catalyst

0.94

 memorable

0.91

 fateful

0.89

 boon

0.87

Activations Density 0.171%

the article "a"

No Comments

No Known Activations