INDEX

Explanations

the word "ham" combined with a number

oai_token-act-pair · gpt-3.5-turbo

references to the name "Birmingham" or related geographical terms

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

uary

-0.73

atively

-0.65

ELF

-0.64

Æ

-0.63

ahead

-0.62

cius

-0.62

REDACTED

-0.57

VO

-0.57

PLAY

-0.56

inventoryQuantity

-0.56

POSITIVE LOGITS

pton

1.81

mers

1.30

ilton

1.27

sburg

1.17

monds

1.17

enei

1.14

shire

1.12

sted

1.10

MER

1.07

med

1.04

Activations Density 0.051%

the word "ham" combined with a number

references to the name "Birmingham" or related geographical terms

No Known Activations