INDEX

Explanations

terms related to specificity and differentiation in various contexts

oai_token-act-pair · gpt-3.5-turbo

specific nouns related to various subjects and items in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

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

iths

-0.68

ryu

-0.66

luaj

-0.64

comings

-0.63

unknown

-0.63

ForgeModLoader

-0.63

bos

-0.63

 Horses

-0.60

 Cosponsors

-0.59

 Clouds

-0.58

POSITIVE LOGITS

 imaginable

1.64

 except

1.12

 conceivable

1.04

 individually

1.01

 ounce

0.90

except

0.88

soever

0.81

winner

0.76

 inch

0.76

 thereafter

0.76

Activations Density 0.195%

terms related to specificity and differentiation in various contexts

specific nouns related to various subjects and items in discussions

No Comments

No Known Activations