INDEX

Explanations

information related to rankings and superlatives

oai_token-act-pair · gpt-3.5-turbo

descriptions of significant entities and rankings

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

erent

-0.82

umblr

-0.76

aleb

-0.75

yden

-0.74

ebus

-0.71

ãĤĮ

-0.69

zin

-0.68

inge

-0.67

inges

-0.67

ices

-0.67

POSITIVE LOGITS

 EVER

0.86

ever

0.83

 surpass

0.78

 unparalleled

0.76

 Genie

0.75

 ever

0.74

 unmatched

0.73

aceae

0.72

behind

0.72

 globally

0.71

Activations Density 0.562%

information related to rankings and superlatives

descriptions of significant entities and rankings

No Comments

No Known Activations