INDEX

Explanations

words related to data collection and potentially privacy violations

oai_token-act-pair · gpt-3.5-turbo

conjunctions, specifically the word "and."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

icago

-0.77

YY

-0.76

blogspot

-0.75

ItemThumbnailImage

-0.74

 Porsche

-0.74

iates

-0.73

enne

-0.71

apesh

-0.70

HDL

-0.68

iator

-0.68

POSITIVE LOGITS

TPPStreamerBot

0.72

opers

0.66

aler

0.66

 Jefferson

0.64

ollah

0.63

 tumble

0.62

 nurture

0.61

ometric

0.61

ink

0.60

alcohol

0.60

Activations Density 0.240%

words related to data collection and potentially privacy violations

conjunctions, specifically the word "and."

No Comments

No Known Activations