INDEX

Explanations

names of political figures

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'R'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

grass

-0.74

ãĥ¼ãĥĨãĤ£

-0.71

 Nieto

-0.70

glers

-0.69

 Totem

-0.69

 Guinness

-0.68

enegger

-0.67

 Dolphin

-0.66

CPR

-0.66

 Granger

-0.65

POSITIVE LOGITS

senal

1.29

ansom

1.18

acing

1.15

ework

1.09

outing

1.08

ICH

1.07

outine

1.06

agnar

1.05

acco

1.04

ascal

1.02

Activations Density 0.032%

names of political figures

occurrences of the letter 'R'

No Comments

No Known Activations