INDEX

Explanations

interesting information or content

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "interesting"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

oise

-0.78

helle

-0.77

heed

-0.74

redited

-0.71

eded

-0.71

required

-0.70

uts

-0.70

otent

-0.69

aper

-0.69

reditation

-0.69

POSITIVE LOGITS

tid

0.89

 Flavoring

0.87

 twists

0.84

arios

0.83

 sidel

0.78

 insights

0.77

 trivia

0.75

 anecdotes

0.71

 observations

0.70

 curiosity

0.69

Activations Density 0.037%

interesting information or content

occurrences of the word "interesting"

No Comments

No Known Activations