INDEX

Explanations

references to Amazon Prime services or products

oai_token-act-pair · gpt-3.5-turbo

references to "Prime" 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

anwhile

-0.86

ciplinary

-0.80

rouch

-0.71

arettes

-0.71

anners

-0.70

INESS

-0.69

ocket

-0.69

 clipboard

-0.69

okia

-0.68

prus

-0.68

POSITIVE LOGITS

knit

1.06

val

0.81

 Directive

0.81

Rib

0.79

 Prime

0.74

thood

0.73

 Minister

0.71

digy

0.71

prime

0.69

0.68

Activations Density 0.011%

references to Amazon Prime services or products

references to "Prime" in various contexts

No Comments

No Known Activations