INDEX

Explanations

references to General Motors (GM) at different levels of importance, such as GM being mentioned in different contexts or GM's business decisions

oai_token-act-pair · gpt-3.5-turbo

mentions of General Motors and related themes

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

Negative Logits

lihood

-0.68

sell

-0.68

 Elixir

-0.66

lies

-0.66

 guiIcon

-0.63

rend

-0.61

 Niet

-0.60

 Wiley

-0.59

cir

-0.59

 claimant

-0.58

POSITIVE LOGITS

GM

1.35

IFIC

0.82

asonic

0.79

APH

0.78

HS

0.77

WARE

0.76

ERA

0.76

ilst

0.75

isoft

0.75

DERR

0.74

Activations Density 0.007%

references to General Motors (GM) at different levels of importance, such as GM being mentioned in different contexts or GM's business decisions

mentions of General Motors and related themes

No Known Activations