INDEX

Explanations

phrases related to angular concepts

oai_token-act-pair · gpt-3.5-turbo

mentions of "Ang," "Angular," and "Angry."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 crypt

-0.77

 FedEx

-0.73

 Waters

-0.71

 cheese

-0.71

 supplemental

-0.71

Zot

-0.71

ttes

-0.69

 password

-0.68

 caps

-0.67

tsky

-0.67

POSITIVE LOGITS

Ang

3.89

 Angular

1.93

Ang

1.85

angular

1.65

ANG

1.58

 Angry

1.57

 Angle

1.44

ang

1.44

 angular

1.43

ang

1.27

Activations Density 0.015%

phrases related to angular concepts

mentions of "Ang," "Angular," and "Angry."

No Comments

No Known Activations