INDEX

Explanations

mentions of words related to an official or organization, possibly news-related

oai_token-act-pair · gpt-3.5-turbo

references to agencies or organizations involved in reporting news or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Reviewed

-0.85

 litter

-0.79

glers

-0.72

cells

-0.62

anchester

-0.61

rawler

-0.61

entin

-0.61

ichick

-0.59

bery

-0.58

NESS

-0.58

POSITIVE LOGITS

 Pradesh

0.82

vantage

0.76

Pwr

0.75

Allah

0.74

llah

0.74

etus

0.68

bia

0.67

Zen

0.67

tur

0.66

èĢħ

0.66

Activations Density 0.447%

mentions of words related to an official or organization, possibly news-related

references to agencies or organizations involved in reporting news or events

No Comments

No Known Activations