INDEX

Explanations

the word "to" at a high activation level

oai_token-act-pair · gpt-3.5-turbo

phrases that express opportunities or permissions

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

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

due

-0.64

 Rahman

-0.64

 Advertisement

-0.63

enance

-0.62

audi

-0.62

 Current

-0.61

payment

-0.60

 incoming

-0.59

going

-0.59

 Else

-0.58

POSITIVE LOGITS

 grips

1.26

asted

0.92

 hear

0.91

 know

0.84

see

0.84

 choose

0.82

axy

0.81

 enjoy

0.80

 explore

0.79

 crawl

0.79

Activations Density 0.040%

the word "to" at a high activation level

phrases that express opportunities or permissions

No Comments

No Known Activations