INDEX

Explanations

instances of repeated phrases or structures, particularly those that indicate sequences of events

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

ufact

-0.83

orney

-0.70

ãĥ¤

-0.70

 Lauder

-0.69

anamo

-0.67

obin

-0.66

vironments

-0.65

 Subcommittee

-0.64

roots

-0.63

illin

-0.62

POSITIVE LOGITS

ago

0.72

 before

0.70

 since

0.68

 consecut

0.67

dies

0.65

 ..........

0.63

 involving

0.63

nd

0.62

Ĥİ

0.62

ifiable

0.60

Activations Density 0.006%

instances of repeated phrases or structures, particularly those that indicate sequences of events

No Comments

No Known Activations