INDEX

Explanations

names and places related to territories and government positions

oai_token-act-pair · gpt-3.5-turbo

references to specific names and terms related to geography or people

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

ndra

-0.79

merce

-0.78

aptic

-0.77

ĺħ

-0.75

ograp

-0.73

ortion

-0.68

 McAuliffe

-0.68

ographics

-0.68

pelled

-0.67

rha

-0.67

POSITIVE LOGITS

 Lans

0.97

ecake

0.76

hell

0.74

 Barcl

0.71

FORE

0.69

FE

0.67

ãĥĢ

0.67

FIN

0.67

better

0.66

brow

0.66

Activations Density 0.021%

names and places related to territories and government positions

references to specific names and terms related to geography or people

No Comments

No Known Activations