INDEX

Explanations

locations or events related to a place named Calaveras

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the word "aver" possibly related to averages, assessments, or summaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

estinal

-0.80

ĪĴ

-0.74

fixes

-0.72

eln

-0.68

orem

-0.65

printed

-0.65

 dietary

-0.65

efe

-0.64

 physicians

-0.64

 Zucker

-0.63

POSITIVE LOGITS

vier

0.95

TAIN

0.88

ionage

0.83

ider

0.81

Â¯Â¯

0.81

ikan

0.81

mint

0.80

anza

0.78

idge

0.75

ihara

0.74

Activations Density 0.020%

locations or events related to a place named Calaveras

repeated mentions of the word "aver" possibly related to averages, assessments, or summaries

No Comments

No Known Activations