INDEX

Explanations

approximate numerical values

oai_token-act-pair · gpt-3.5-turbo

approximations or estimations related to quantities and measurements

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

oli

-0.72

ters

-0.68

ieu

-0.65

arella

-0.61

alez

-0.61

rive

-0.61

iments

-0.59

ves

-0.59

ousel

-0.58

 decidedly

-0.58

POSITIVE LOGITS

 analogous

0.95

 equivalent

0.84

 contempor

0.81

0.78

 speaking

0.76

0.75

HAL

0.74

 eighty

0.74

 midway

0.72

Activations Density 0.035%

approximate numerical values

approximations or estimations related to quantities and measurements

No Comments

No Known Activations