INDEX

Explanations

proper nouns, particularly the name "Russell."

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Russell."

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

glers

-0.72

 attendant

-0.71

bid

-0.70

alach

-0.69

displayText

-0.69

cale

-0.68

venture

-0.65

 hypers

-0.65

 willful

-0.65

 copying

-0.65

POSITIVE LOGITS

 Westbrook

1.02

 Wilson

0.95

ieth

0.86

ville

0.85

ian

0.85

ians

0.82

 Peters

0.82

inson

0.81

ership

0.81

sburg

0.80

Activations Density 0.011%

proper nouns, particularly the name "Russell."

mentions of the name "Russell."

No Comments

No Known Activations