INDEX

Explanations

terms related to user interactions and functionality in an app or platform

oai_token-act-pair · gpt-3.5-turbo

user interactions and activities within digital platforms or applications

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

catentry

-0.76

 fuckin

-0.64

laughter

-0.63

RIP

-0.60

lon

-0.60

 blah

-0.60

jah

-0.59

Defense

-0.58

Very

-0.58

amation

-0.58

POSITIVE LOGITS

 themselves

1.15

 their

1.00

 anonymously

0.89

 avatar

0.88

selves

0.85

their

0.82

 selves

0.81

UGC

0.76

 individually

0.74

earable

0.73

Activations Density 0.701%

terms related to user interactions and functionality in an app or platform

user interactions and activities within digital platforms or applications

No Comments

No Known Activations