INDEX

Explanations

terms related to political and social conflict, especially those involving threats and criticism

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

chaos, agitation, or misinformation

np_acts-logits-general · gemini-2.0-flash

negative discourse escalation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

AndEndTag

-0.79

 ftate

-0.69

 Majefty

-0.69

InjectAttribute

-0.67

 consommateurs

-0.66

 fubject

-0.65

 purpoſe

-0.64

 occafion

-0.64

 ſtate

-0.63

 laikā

-0.62

POSITIVE LOGITS

 frantic

0.84

 cries

0.83

 speculation

0.79

 constant

0.77

 sighs

0.76

 intense

0.75

 heated

0.75

 confusion

0.75

 shouting

0.74

 finger

0.74

Activations Density 0.525%

terms related to political and social conflict, especially those involving threats and criticism

chaos, agitation, or misinformation

negative discourse escalation

No Comments

No Known Activations