INDEX

Explanations

phrases describing methods or ways of doing things

oai_token-act-pair · gpt-3.5-turbo

the word "in" used in various contexts

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

ŃĶ

-0.61

rina

-0.54

stasy

-0.53

 SOLD

-0.53

iery

-0.53

requency

-0.53

 Lear

-0.53

 Wife

-0.53

ernel

-0.52

 originals

-0.52

POSITIVE LOGITS

roads

0.89

 which

0.87

humane

0.81

 somew

0.80

effic

0.79

which

0.73

 advance

0.73

ject

0.72

clus

0.72

 Which

0.72

Activations Density 0.151%

phrases describing methods or ways of doing things

the word "in" used in various contexts

No Comments

No Known Activations