INDEX

Explanations

comparisons between different subjects or situations

oai_token-act-pair · gpt-3.5-turbo

comparisons between different subjects or situations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ainer

-0.74

iott

-0.72

ANCE

-0.70

ategor

-0.67

YD

-0.66

esses

-0.66

SO

-0.63

lyak

-0.63

EV

-0.62

 INCLUD

-0.61

POSITIVE LOGITS

 favorably

0.70

 ours

0.70

 afar

0.69

 comparable

0.66

 objectively

0.65

 alternatives

0.65

 scrim

0.65

inventoryQuantity

0.64

 Hath

0.63

BuyableInstoreAndOnline

0.63

Activations Density 0.112%

comparisons between different subjects or situations

comparisons between different subjects or situations

No Comments

No Known Activations