INDEX

Explanations

images or visual content

oai_token-act-pair · gpt-3.5-turbo

references to viewing and managing visual content or data

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

DN

-0.76

Pwr

-0.74

eros

-0.69

iasco

-0.67

aughs

-0.67

 calf

-0.64

Fas

-0.63

aughed

-0.63

amins

-0.63

XL

-0.62

POSITIVE LOGITS

ĸļ

0.79

 VIDEOS

0.78

selves

0.71

 favorably

0.71

 Preferences

0.70

 preferences

0.70

 Judgment

0.70

 viewpoint

0.67

 impartial

0.67

 Orient

0.66

Activations Density 0.140%

images or visual content

references to viewing and managing visual content or data

No Comments

No Known Activations