INDEX

Explanations

words related to reviewing or rewatching content

oai_token-act-pair · gpt-3.5-turbo

references to replays in various contexts, particularly in sports and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

mA

-0.83

kie

-0.77

 Citiz

-0.69

Cola

-0.69

 Milo

-0.68

å§«

-0.68

rosso

-0.68

afort

-0.66

 Advertisement

-0.66

ju

-0.65

POSITIVE LOGITS

 replay

3.42

arted

1.57

 deposition

1.13

ived

1.00

 thriller

0.94

 Hitchcock

0.92

 reel

0.89

 examiner

0.87

 helpless

0.85

 slides

0.81

Activations Density 0.035%

words related to reviewing or rewatching content

references to replays in various contexts, particularly in sports and media

No Comments

No Known Activations