INDEX

Explanations

phrases related to putting on something like clothes or accessories

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "put on" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ESA

-0.65

 prox

-0.63

llah

-0.59

NRS

-0.58

Zen

-0.57

 Rounds

-0.57

=]

-0.57

ELF

-0.56

Xi

-0.56

 holiest

-0.56

POSITIVE LOGITS

 airs

0.94

 weight

0.75

*/(

0.74

shirts

0.74

erous

0.74

sk

0.73

unci

0.72

shirt

0.71

 mascara

0.71

sung

0.69

Activations Density 0.032%

phrases related to putting on something like clothes or accessories

instances of the phrase "put on" in various contexts

No Comments

No Known Activations