INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names or titles associated with individuals or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Eliot

-0.72

 Appalach

-0.66

 Zion

-0.64

 Kitty

-0.64

HMS

-0.63

 Beacon

-0.62

 Sussex

-0.60

 Springfield

-0.59

 Harold

-0.59

 Bones

-0.58

POSITIVE LOGITS

ondo

1.16

udo

1.10

Ã¡

1.07

ado

1.04

Ã£o

1.04

iola

1.02

ito

1.02

Ã±o

1.02

Ã³n

1.02

agna

1.01

Activations Density 0.141%

names of individuals

proper nouns, particularly names or titles associated with individuals or roles

No Comments

No Known Activations