INDEX

Explanations

proper nouns related to specific locations or people

oai_token-act-pair · gpt-3.5-turbo

references to locations and notable figures

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

Not in Any Lists

No Comments

Negative Logits

ibaba

-0.70

unks

-0.68

ez

-0.64

ranged

-0.63

ãĥĬ

-0.63

imony

-0.62

ãĥīãĥ©ãĤ´ãĥ³

-0.62

zai

-0.62

unk

-0.62

yk

-0.61

POSITIVE LOGITS

2.24

1.92

1.59

Cs

1.41

1.40

Ce

1.29

Ci

1.24

CK

1.23

CIS

1.23

CCC

1.23

Activations Density 0.745%

proper nouns related to specific locations or people

references to locations and notable figures

No Comments

No Known Activations