INDEX

Explanations

words related to motor activities or vehicles

oai_token-act-pair · gpt-3.5-turbo

references to motor-related concepts or terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Foley

-0.77

 Michaels

-0.76

 Caesar

-0.70

 Dynasty

-0.70

 Alibaba

-0.69

 Carbuncle

-0.68

 Ming

-0.68

romeda

-0.67

ereo

-0.67

 Bowie

-0.66

POSITIVE LOGITS

bike

1.32

otor

1.15

cycl

1.12

cycle

1.12

puter

1.03

chair

0.97

wheel

0.95

boats

0.92

ized

0.90

netic

0.89

Activations Density 0.011%

words related to motor activities or vehicles

references to motor-related concepts or terminology

No Comments

No Known Activations