INDEX

Explanations

keywords related to marking or labeling

oai_token-act-pair · gpt-3.5-turbo

terms related to markers and plaques used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ategory

-0.94

orld

-0.89

ONSORED

-0.86

quished

-0.82

é¾

-0.80

iannopoulos

-0.80

ILLE

-0.78

acia

-0.77

Kut

-0.76

apest

-0.75

POSITIVE LOGITS

 marker

1.23

 markers

1.19

posts

0.93

 plaque

0.78

 marking

0.73

 Carney

0.72

 Twain

0.70

 pens

0.68

holder

0.68

 blank

0.67

Activations Density 0.016%

keywords related to marking or labeling

terms related to markers and plaques used in various contexts

No Comments

No Known Activations