INDEX

Explanations

references to cannons or cannon-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to cannons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

©¶æ

-0.95

lihood

-0.92

DragonMagazine

-0.82

æĸ¹

-0.79

 Agents

-0.76

Else

-0.75

çīĪ

-0.73

éĹ

-0.71

 Genetics

-0.70

ele

-0.69

POSITIVE LOGITS

balls

1.22

lance

1.10

ball

1.03

 fodder

1.02

ibal

0.84

otine

0.83

ulic

0.78

nels

0.77

zeb

0.76

powder

0.75

Activations Density 0.030%

references to cannons or cannon-related terms

terms related to cannons

No Comments

No Known Activations