INDEX

Explanations

prominent names associated with the content of the document

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

proper names, likely related to individuals in different contexts

oai_token-act-pair · gpt-3.5-turbo

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

teenth

-0.79

auga

-0.76

 curfew

-0.73

soDeliveryDate

-0.69

orie

-0.67

angular

-0.67

nant

-0.65

uracy

-0.64

perature

-0.63

 hikers

-0.62

POSITIVE LOGITS

stein

1.30

feld

1.09

baum

0.98

berg

0.98

 Katz

0.91

bard

0.90

wald

0.86

itsch

0.85

owitz

0.80

bach

0.80

Activations Density 0.065%

prominent names associated with the content of the document

proper names, likely related to individuals in different contexts

No Comments

No Known Activations