INDEX

Explanations

mentions instructing or receiving something in a document, potentially related to terms of use or agreements

oai_token-act-pair · gpt-3.5-turbo

references to the reader or the second person

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

 Gamb

-0.57

adium

-0.57

 Prelude

-0.56

 moot

-0.56

 Philipp

-0.56

parts

-0.56

 Faust

-0.54

itism

-0.54

 Defenders

-0.53

 Chap

-0.52

POSITIVE LOGITS

're

1.10

'll

1.00

've

0.96

'd

0.85

may

0.82

can

0.81

hei

0.80

 must

0.76

 MUST

0.75

 cannot

0.70

Activations Density 0.071%

mentions instructing or receiving something in a document, potentially related to terms of use or agreements

references to the reader or the second person

No Comments

No Known Activations