INDEX

Explanations

questions directed towards the reader

oai_token-act-pair · gpt-3.5-turbo

questions directed towards the reader

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

enges

-0.70

ocol

-0.70

 Vill

-0.68

Lago

-0.60

ĸļ

-0.59

ylum

-0.58

 Hels

-0.58

iki

-0.57

 Sale

-0.56

 Absent

-0.56

POSITIVE LOGITS

 guys

1.16

 think

1.04

 prefer

0.97

 propose

0.92

 reckon

0.91

 anticipate

0.89

 believe

0.85

 recommend

0.82

 want

0.81

 feel

0.81

Activations Density 0.041%

questions directed towards the reader

questions directed towards the reader

No Comments

No Known Activations