INDEX

Explanations

instances where credit is being given or deserved

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

nel

-0.69

atos

-0.64

chan

-0.61

icz

-0.61

 contracting

-0.60

IRE

-0.59

viol

-0.56

 entangled

-0.55

inj

-0.55

 Alter

-0.55

POSITIVE LOGITS

ability

0.75

giving

0.75

worthiness

0.74

abilities

0.74

ibly

0.73

itism

0.71

cards

0.70

 credits

0.70

ably

0.69

orable

0.69

Activations Density 0.039%

instances where credit is being given or deserved

No Comments

No Known Activations