INDEX

Explanations

terms related to political 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Skocz

-0.65

cha

-0.63

Fprintf

-0.61

 Irma

-0.59

Cha

-0.54

alha

-0.53

Cha

-0.52

fraz

-0.52

();?>

-0.52

chay

-0.52

POSITIVE LOGITS

 candidates

3.91

 candidate

3.85

 Candidates

3.59

 Candidate

3.56

Candidate

3.39

candidate

3.36

Candidates

3.33

candidates

3.29

 CANDIDATE

3.14

 candidatos

2.68

Activations Density 0.056%

terms related to political candidates and nominations

No Comments

No Known Activations