INDEX

Explanations

the word "other" appearing in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to additional items or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.74

utenant

-0.67

 Kubrick

-0.66

ister

-0.65

 Tiff

-0.65

creen

-0.64

 Rouge

-0.64

 Cycling

-0.64

 Jaguar

-0.63

pload

-0.63

POSITIVE LOGITS

worldly

1.61

 assorted

1.06

 aspects

1.01

 forms

0.99

 kinds

0.96

 types

0.93

 factors

0.92

 facets

0.90

 considerations

0.88

artifacts

0.88

Activations Density 0.065%

the word "other" appearing in various contexts

references to additional items or categories

No Comments

No Known Activations