INDEX

Explanations

sentences indicating a specific consequence or result

oai_token-act-pair · gpt-3.5-turbo

statements indicating certainty or inevitability

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

 Saud

-0.69

¿½

-0.65

Suggest

-0.64

adh

-0.61

Newsletter

-0.60

igor

-0.60

ĪĴ

-0.58

mbuds

-0.56

 charact

-0.56

Winged

-0.56

POSITIVE LOGITS

eday

0.72

pora

0.72

 someday

0.71

 automatically

0.70

 usable

0.70

 liable

0.68

'll

0.67

 avoided

0.65

owe

0.65

 shouldn

0.65

Activations Density 0.266%

sentences indicating a specific consequence or result

statements indicating certainty or inevitability

No Comments

No Known Activations