INDEX

Explanations

mentions of the concept of "scaling" in various contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to scaling and growth

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vous

-0.73

algia

-0.68

riad

-0.68

naire

-0.65

toc

-0.65

bda

-0.63

present

-0.63

odor

-0.63

 Marcos

-0.62

Ñı

-0.62

POSITIVE LOGITS

 scale

0.90

 scaled

0.85

itized

0.83

 heights

0.83

Factor

0.80

 proportions

0.79

 scales

0.77

Scale

0.76

 ambitions

0.76

 scaling

0.73

Activations Density 0.015%

mentions of the concept of "scaling" in various contexts

terms related to scaling and growth

No Comments

No Known Activations