INDEX

Explanations

references to a specific entity named "United"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "United"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ouf

-0.69

prus

-0.69

MY

-0.66

tnc

-0.65

pmwiki

-0.65

aign

-0.63

 Wink

-0.63

EGIN

-0.63

umen

-0.62

bard

-0.61

POSITIVE LOGITS

 Nations

1.13

 States

1.13

 Methodist

1.05

 Airlines

1.03

 STATES

0.95

sburg

0.89

States

0.89

Health

0.83

 Launch

0.80

 Artists

0.77

Activations Density 0.034%

references to a specific entity named "United"

occurrences of the word "United"

No Comments

No Known Activations