INDEX

Explanations

references to individuals with the surname "Bin Laden."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Bin Laden" and related references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Ross

-0.85

 pall

-0.81

 Corinth

-0.77

 crest

-0.74

 Ross

-0.72

aunders

-0.71

abilia

-0.70

 Rosenthal

-0.70

 balk

-0.69

mur

-0.69

POSITIVE LOGITS

:\

2.13

Bin

1.64

epend

1.55

edar

1.27

 Nuclear

1.27

eper

1.03

 Install

1.02

ename

1.01

anium

1.00

 Cedar

0.93

Activations Density 0.058%

references to individuals with the surname "Bin Laden."

occurrences of the name "Bin Laden" and related references

No Comments

No Known Activations