INDEX

Explanations

phrases related to assessments and evaluations

oai_token-act-pair · gpt-3.5-turbo

terms related to evaluations and assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 includ

-0.87

ilial

-0.72

 destro

-0.70

acht

-0.68

cape

-0.66

APTER

-0.65

amd

-0.64

 carnage

-0.64

sin

-0.64

 racket

-0.62

POSITIVE LOGITS

 evaluations

1.13

untarily

0.72

 Metroid

0.68

 stickers

0.65

 stamps

0.63

Gender

0.63

Lia

0.63

lex

0.62

 Benefits

0.61

 passports

0.61

Activations Density 0.002%

phrases related to assessments and evaluations

terms related to evaluations and assessments

No Comments

No Known Activations