INDEX

Explanations

references to the word "Sar"

oai_token-act-pair · gpt-3.5-turbo

the repetitive mention of the term "Sar."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 curfew

-0.70

 Lovecraft

-0.69

 flourish

-0.68

 habitable

-0.63

éĹĺ

-0.62

STER

-0.60

 numbering

-0.59

 sterling

-0.59

 Dangerous

-0.59

 developmental

-0.59

POSITIVE LOGITS

kees

1.32

andon

1.09

ban

1.07

pling

1.04

wark

1.02

atos

1.00

ashtra

0.99

thal

0.98

vati

0.98

ussian

0.96

Activations Density 0.023%

references to the word "Sar"

the repetitive mention of the term "Sar."

No Comments

No Known Activations