INDEX

Explanations

references to politics and its various facets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 jurk

-0.66

endregion

-0.66

Extinguishing

-0.65

istoitu

-0.64

Datuak

-0.63

IsPostBack

-0.61

blox

-0.59

rénées

-0.58

 Publik

-0.58

amerikanischer

-0.58

POSITIVE LOGITS

 politics

1.55

 economics

1.47

politics

1.28

 Politics

1.22

 physics

1.21

 geography

1.19

economics

1.19

Politics

1.13

 Economics

1.13

Economics

1.12

Activations Density 0.253%

references to politics and its various facets

No Comments

No Known Activations