INDEX

Explanations

terms related to indexing and databases

oai_token-act-pair · gpt-3.5-turbo

references to indexing or index-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soDeliveryDate

-0.87

overs

-0.74

isSpecialOrderable

-0.72

uggage

-0.70

 Honour

-0.69

zech

-0.65

sei

-0.65

bilt

-0.65

 behav

-0.65

atu

-0.63

POSITIVE LOGITS

 mund

0.86

uated

0.80

icals

0.80

 finger

0.78

ical

0.78

ysis

0.76

ured

0.76

elsen

0.76

ilation

0.74

urance

0.74

Activations Density 0.042%

terms related to indexing and databases

references to indexing or index-related concepts

No Comments

No Known Activations