INDEX

Explanations

abbreviations for various items or categories

oai_token-act-pair · gpt-3.5-turbo

references to common items or categories indicated by "etc."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

adows

-0.66

 Lords

-0.61

mp

-0.61

 skies

-0.61

 shadow

-0.61

gd

-0.60

 parliament

-0.58

poke

-0.58

 backyard

-0.57

irlfriend

-0.57

POSITIVE LOGITS

etc

1.27

etc

1.08

gow

0.91

.?

0.88

 indo

0.84

icter

0.84

imei

0.84

eter

0.83

.,

0.83

querque

0.83

Activations Density 0.023%

abbreviations for various items or categories

references to common items or categories indicated by "etc."

No Comments

No Known Activations