INDEX

Explanations

mentions of the name "Osama bin Laden"

oai_token-act-pair · gpt-3.5-turbo

references to Osama bin Laden

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Amazing

-0.74

terday

-0.74

anwhile

-0.71

theless

-0.64

LU

-0.63

IRO

-0.63

Premium

-0.62

pter

-0.62

 Parish

-0.62

BLE

-0.62

POSITIVE LOGITS

ocular

1.58

omial

1.48

 Laden

1.26

bin

1.17

 bins

0.99

mates

0.89

utils

0.88

Bin

0.84

ning

0.84

thood

0.83

Activations Density 0.005%

mentions of the name "Osama bin Laden"

references to Osama bin Laden

No Comments

No Known Activations