INDEX

Explanations

phrases related to the intuitive nature or usability of something

oai_token-act-pair · gpt-3.5-turbo

expressions of intuitiveness or intuitive concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

gre

-0.74

mington

-0.73

abad

-0.71

crow

-0.69

annis

-0.68

emetery

-0.68

 Roads

-0.68

fighters

-0.66

ankind

-0.65

dogs

-0.64

POSITIVE LOGITS

ly

1.18

uitive

1.07

 intuitive

1.06

istically

0.90

ically

0.89

istic

0.87

 shortcut

0.84

 disson

0.83

 shortcuts

0.81

intuitive

0.80

Activations Density 0.003%

phrases related to the intuitive nature or usability of something

expressions of intuitiveness or intuitive concepts

No Comments

No Known Activations