INDEX

Explanations

words related to individuals or things named "Cand" or variations of that name

oai_token-act-pair · gpt-3.5-turbo

references to 'candle' or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.74

FactoryReloaded

-0.73

HF

-0.68

 pity

-0.65

FG

-0.61

GV

-0.61

 centrif

-0.61

 disparate

-0.60

ãĤ´ãĥ³

-0.60

 phased

-0.60

POSITIVE LOGITS

idates

1.48

lest

1.30

idate

1.25

les

0.98

ulum

0.95

illo

0.93

raper

0.92

reon

0.91

escent

0.90

encies

0.89

Activations Density 0.022%

words related to individuals or things named "Cand" or variations of that name

references to 'candle' or related terms

No Comments

No Known Activations