INDEX

Explanations

proper nouns related to locations, individuals, and organizations, particularly in the context of government and politics

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

words or fragments related to the name "Waukesha"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

 slam

-0.64

 crunch

-0.54

Chr

-0.51

 bust

-0.51

 dread

-0.51

 distinct

-0.51

 Crunch

-0.50

 Sapphire

-0.50

 soph

-0.49

 conv

-0.48

POSITIVE LOGITS

ipeg

1.10

nesday

1.10

atever

0.94

hester

0.89

ankind

0.87

bledon

0.86

ÅĤ

0.84

itzer

0.81

WT

0.80

cester

0.78

Activations Density 0.169%

proper nouns related to locations, individuals, and organizations, particularly in the context of government and politics

words or fragments related to the name "Waukesha"

No Comments

No Known Activations