INDEX

Explanations

mathematical expressions and symbols

oai_token-act-pair · gpt-3.5-turbo

mathematical expressions or symbols indicating addition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Nare

-0.69

 Sparkle

-0.68

ruary

-0.64

 Dise

-0.64

opathic

-0.64

pace

-0.63

Runner

-0.63

 Grimes

-0.63

 Turing

-0.62

 Petty

-0.61

POSITIVE LOGITS

++++++++++++++++

1.36

-+-+-+-+

1.30

++++

1.11

/+

1.06

++++++++

0.99

--+

0.95

-+

0.95

/-

0.90

--------------------------------

0.78

union

0.77

Activations Density 0.021%

mathematical expressions and symbols

mathematical expressions or symbols indicating addition

No Comments

No Known Activations