INDEX

Explanations

terms and phrases related to voting and political actions

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

votes and numbers

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

IMPORTED

-0.56

+#+#

-0.51

zad

-0.46

enste

-0.46

ser

-0.45

 model

-0.44

IPT

-0.44

 MERCHANTABILITY

-0.44

 meta

-0.42

cci

-0.42

POSITIVE LOGITS

ponses

0.76

 votes

0.71

XmlAccessType

0.71

 quorum

0.71

WithIOException

0.70

addGap

0.68

 unanim

0.67

 unanimous

0.66

Hentet

0.66

 vote

0.65

Activations Density 0.070%

terms and phrases related to voting and political actions

votes and numbers

No Comments

No Known Activations