INDEX

Explanations

phrases related to the surname "Trump."

oai_token-act-pair · gpt-3.5-turbo

instances of "trumps" and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

raq

-0.71

RW

-0.66

scape

-0.63

Blade

-0.63

BIT

-0.62

Sop

-0.61

Die

-0.59

joice

-0.58

chie

-0.58

ghan

-0.57

POSITIVE LOGITS

umps

1.32

umping

0.87

hift

0.83

umped

0.79

pell

0.77

ules

0.77

ump

0.75

peed

0.75

etsk

0.74

uge

0.74

Activations Density 0.006%

phrases related to the surname "Trump."

instances of "trumps" and related terminology

No Comments

No Known Activations