INDEX

Explanations

proper nouns and names, likely related to a specific person or character named "Im" at various levels of importance

oai_token-act-pair · gpt-3.5-turbo

the verb "im."

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

NetMessage

-0.84

chnology

-0.73

 Forsaken

-0.63

 grease

-0.63

 Parenthood

-0.62

¬¼

-0.61

 brace

-0.60

meal

-0.60

 Nicarag

-0.60

ttes

-0.59

POSITIVE LOGITS

perial

1.26

ple

1.25

enez

1.25

agine

1.22

bledon

1.16

ply

1.14

psons

1.11

mediately

1.10

ples

1.09

pson

1.09

Activations Density 0.052%

proper nouns and names, likely related to a specific person or character named "Im" at various levels of importance

the verb "im."

No Comments

No Known Activations