INDEX

Explanations

names with a specific pattern: ending with "zan" or "ich"

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names associated with individuals and companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UCT

-0.76

ascript

-0.76

ivably

-0.67

aliation

-0.65

Db

-0.64

 Thumbnails

-0.63

 merc

-0.62

 medic

-0.62

iencies

-0.60

 fict

-0.60

POSITIVE LOGITS

itsch

1.09

inski

1.07

owski

1.05

itzer

1.00

insky

0.96

owsky

0.95

ewski

0.95

nik

0.92

gaard

0.91

ovsky

0.89

Activations Density 0.221%

names with a specific pattern: ending with "zan" or "ich"

proper nouns, specifically names associated with individuals and companies

No Comments

No Known Activations