INDEX

Explanations

phrases related to expression of opinions or explanations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the potential for learning or improvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ahime

-0.70

majority

-0.69

trak

-0.68

ser

-0.62

motion

-0.62

handedly

-0.61

 majority

-0.60

aten

-0.60

 appropri

-0.58

ffe

-0.58

POSITIVE LOGITS

 glean

0.83

 Learned

0.70

 besides

0.69

antine

0.69

 Flavoring

0.68

ibaba

0.66

pection

0.65

aina

0.65

rous

0.62

ntil

0.62

Activations Density 0.261%

phrases related to expression of opinions or explanations

phrases indicating the potential for learning or improvement

No Comments

No Known Activations