INDEX

Explanations

specific geographic locations within a wider area

oai_token-act-pair · gpt-3.5-turbo

phrases that identify different regions or parts of a location or society

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

sonian

-0.62

 invitation

-0.59

iasis

-0.59

gee

-0.59

sy

-0.58

 induction

-0.58

roma

-0.57

apt

-0.57

Spl

-0.56

ulus

-0.56

POSITIVE LOGITS

 thereof

1.00

cale

0.89

chool

0.88

 areas

0.86

 bordering

0.83

of

0.83

 regions

0.82

region

0.82

pace

0.81

outhern

0.81

Activations Density 0.128%

specific geographic locations within a wider area

phrases that identify different regions or parts of a location or society

No Comments

No Known Activations