INDEX

Explanations

mentions of films, TV shows, and actors

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

NRS

-0.80

enta

-0.76

ollah

-0.74

cffffcc

-0.74

merga

-0.73

Methods

-0.72

wcs

-0.70

ertodd

-0.70

rawdownloadcloneembedreportprint

-0.69

RF

-0.69

POSITIVE LOGITS

 starring

1.30

 featuring

1.04

 wherein

1.04

 Sleeping

1.00

 which

0.95

 narrated

0.94

 Episode

0.88

 titled

0.88

 released

0.87

 Tales

0.86

Activations Density 0.187%

mentions of films, TV shows, and actors

punctuation marks, particularly commas

No Comments

No Known Activations