INDEX

Explanations

numerical references and identifiers related to content or data structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.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

 streng

-0.75

 Palest

-0.73

hel

-0.71

 encour

-0.71

 Stoke

-0.68

Esk

-0.66

 Fitz

-0.65

 compan

-0.63

lif

-0.62

 estab

-0.60

POSITIVE LOGITS

0.81

0000000000000000

0.81

è¯

0.77

0.76

Thumbnail

0.75

inx

0.74

00000000

0.73

0.72

????????

0.72

"]=>

0.70

Activations Density 0.041%

numerical references and identifiers related to content or data structure

No Comments

No Known Activations