INDEX

Explanations

adjectives related to evaluation and quality

oai_token-act-pair · gpt-3.5-turbo

terms associated with value or desirability, particularly in reference to people or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Ĥª

-0.68

 Annotations

-0.63

Vote

-0.62

channelAvailability

-0.61

angan

-0.58

anni

-0.56

SPONSORED

-0.56

 Rally

-0.55

 Simulator

-0.55

Station

-0.55

POSITIVE LOGITS

own

0.99

paren

0.88

entious

0.86

gling

0.86

icular

0.84

escription

0.84

dit

0.83

uc

0.82

eem

0.81

inal

0.74

Activations Density 0.250%

adjectives related to evaluation and quality

terms associated with value or desirability, particularly in reference to people or items

No Comments

No Known Activations