INDEX

Explanations

mathematical, temporal, or consequential ultimatums

oai_token-act-pair · gpt-3.5-turbo

references to ultimate or ultimatum concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Footnote

-0.79

ãģĦ

-0.77

keeping

-0.73

Guest

-0.71

 Sins

-0.68

stocks

-0.67

Accessory

-0.65

************

-0.65

SPONSORED

-0.64

xual

-0.64

POSITIVE LOGITS

imates

1.39

raviolet

1.12

rav

0.98

ral

0.96

reme

0.95

imus

0.95

ritional

0.94

ima

0.91

imum

0.91

iple

0.91

Activations Density 0.019%

mathematical, temporal, or consequential ultimatums

references to ultimate or ultimatum concepts

No Comments

No Known Activations