INDEX

Explanations

terms related to the use and disposal of items, such as "disposable", "reusable", "discarded", and "recycled"

oai_token-act-pair · gpt-3.5-turbo

terms related to economic and environmental disposability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

owitz

-0.80

rieg

-0.69

ois

-0.69

xual

-0.66

 secrecy

-0.65

 Played

-0.65

osis

-0.64

mith

-0.64

ohn

-0.64

kers

-0.64

POSITIVE LOGITS

 disposable

1.00

 diapers

0.95

bage

0.92

ibles

0.87

 reused

0.85

 veter

0.76

itures

0.75

adoes

0.74

 aeros

0.74

ink

0.73

Activations Density 0.009%

terms related to the use and disposal of items, such as "disposable", "reusable", "discarded", and "recycled"

terms related to economic and environmental disposability

No Comments

No Known Activations