INDEX

Explanations

names of different individuals or locations

oai_token-act-pair · gpt-3.5-turbo

proper nouns and key terms related to names and entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Perkins

-1.03

PW

-0.97

 Petersen

-0.97

 Pier

-0.81

 Peck

-0.80

 Pixie

-0.77

 Piper

-0.76

 Pioneer

-0.76

 Pearce

-0.75

 Pupp

-0.74

POSITIVE LOGITS

al

1.68

AL

1.65

als

1.40

alis

1.39

alin

1.37

alist

1.33

aled

1.30

ala

1.28

ali

1.27

alg

1.26

Activations Density 0.268%

names of different individuals or locations

proper nouns and key terms related to names and entities

No Comments

No Known Activations