INDEX

Explanations

content related to behind-the-scenes activities or information

oai_token-act-pair · gpt-3.5-turbo

references to behind-the-scenes content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Roth

-0.63

ggies

-0.63

rr

-0.63

heit

-0.63

grave

-0.63

 pound

-0.62

 Polaris

-0.61

 antidepressants

-0.61

thood

-0.60

orough

-0.59

POSITIVE LOGITS

scenes

1.15

 Scenes

0.81

acters

0.80

terday

0.77

 Procedures

0.76

door

0.76

ewitness

0.76

Enlarge

0.73

 Missions

0.73

Dialogue

0.71

Activations Density 0.017%

content related to behind-the-scenes activities or information

references to behind-the-scenes content

No Comments

No Known Activations