INDEX

Explanations

words related to motor functions or motor vehicles

oai_token-act-pair · gpt-3.5-turbo

references to "motor" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Michaels

-0.76

 Foley

-0.72

 Carbuncle

-0.71

 Alibaba

-0.70

 Aval

-0.69

ereo

-0.68

 Osiris

-0.68

 Dynasty

-0.66

 Ming

-0.66

 Caesar

-0.65

POSITIVE LOGITS

bike

1.36

cycle

1.14

cycl

1.10

otor

1.08

chair

1.05

puter

0.99

wheel

0.97

boats

0.97

netic

0.95

boat

0.91

Activations Density 0.015%

words related to motor functions or motor vehicles

references to "motor" in various contexts

No Comments

No Known Activations