INDEX

Explanations

the word "fat" with varying intensities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "fat" 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

SPONSORED

-0.86

 Ascend

-0.75

yrinth

-0.73

 Compass

-0.68

 Rowling

-0.66

 Doct

-0.66

 Aerospace

-0.62

Sensor

-0.61

 Vaugh

-0.61

 Pharmaceutical

-0.60

POSITIVE LOGITS

igue

1.44

hered

1.16

ality

0.94

ima

0.89

uous

0.89

tailed

0.89

ty

0.89

rition

0.86

omas

0.85

wallet

0.83

Activations Density 0.028%

the word "fat" with varying intensities

occurrences of the word "fat" in various contexts

No Comments

No Known Activations