INDEX

Explanations

terms related to candidates and nominations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Sao

-0.66

Diz

-0.65

 HOMES

-0.63

AsUp

-0.63

ffron

-0.63

 Crimes

-0.62

 jail

-0.61

chainId

-0.61

served

-0.60

 StatelessWidget

-0.60

POSITIVE LOGITS

 Candidates

1.26

 candidates

1.26

CAND

1.20

Candidates

1.19

 Candidate

1.18

Candidate

1.17

 CANDIDATE

1.15

 candidate

1.11

candidates

1.08

andidates

1.05

Activations Density 0.124%

terms related to candidates and nominations

No Comments

No Known Activations