INDEX

Explanations

keywords or tags within a text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "tags" and variations related to tagging content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ITNESS

-0.85

owship

-0.79

thritis

-0.72

undai

-0.66

Ave

-0.64

pter

-0.63

croft

-0.62

raising

-0.62

arlane

-0.62

 predec

-0.61

POSITIVE LOGITS

Tags

1.25

 Tags

1.23

tags

1.14

 tags

0.98

ynt

0.84

 tagged

0.82

ystem

0.82

idy

0.81

ynthesis

0.80

 tagging

0.80

Activations Density 0.013%

keywords or tags within a text

instances of the word "tags" and variations related to tagging content

No Comments

No Known Activations