INDEX

Explanations

actions or activities related to food and clothing

oai_token-act-pair · gpt-3.5-turbo

actions related to the consumption and usage of items

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

ĪĴ

-0.62

quickShipAvailable

-0.60

EStreamFrame

-0.60

 Rubin

-0.59

Git

-0.57

yright

-0.56

usha

-0.55

orio

-0.55

anticipated

-0.55

Teg

-0.54

POSITIVE LOGITS

 outdoors

1.00

 everywhere

0.99

 indoors

0.96

 sparing

0.94

 worldwide

0.92

 orally

0.92

 preval

0.90

 concurrently

0.88

 throughout

0.85

 alongside

0.83

Activations Density 0.237%

actions or activities related to food and clothing

actions related to the consumption and usage of items

No Comments

No Known Activations