INDEX

Explanations

phrases indicating statements or arguments

oai_token-act-pair · gpt-3.5-turbo

statements and claims made by individuals

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

estern

-0.82

odcast

-0.79

ocl

-0.75

enum

-0.72

uminati

-0.69

iership

-0.69

peg

-0.69

transfer

-0.69

iffe

-0.68

avorite

-0.68

POSITIVE LOGITS

"[

0.86

it

0.84

 they

0.80

 instead

0.78

"'

0.78

 therein

0.75

 "...

0.73

 that

0.72

"(

0.72

'[

0.71

Activations Density 0.085%

phrases indicating statements or arguments

statements and claims made by individuals

No Comments

No Known Activations