INDEX

Explanations

words related to locations or proper nouns

oai_token-act-pair · gpt-3.5-turbo

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

 Perkins

-1.03

 Petersen

-0.93

PW

-0.89

 Peck

-0.82

 Pier

-0.79

SPD

-0.76

 Schneider

-0.76

 Phys

-0.76

 whist

-0.76

SPI

-0.75

POSITIVE LOGITS

al

1.83

AL

1.78

als

1.53

ala

1.51

alin

1.44

alam

1.40

alis

1.39

ali

1.36

aled

1.36

alg

1.35

Activations Density 0.264%

words related to locations or proper nouns

No Comments

No Known Activations