INDEX

Explanations

terms associated with violence and aggressive behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

NOPQRST

-1.05

 مرئيه

-0.75

cumulative

-0.75

ContentAlignment

-0.74

awtextra

-0.71

 Silber

-0.70

tling

-0.69

 beträgt

-0.68

 Pante

-0.67

 vnto

-0.66

POSITIVE LOGITS

 Paglinawan

1.01

 elegans

0.86

 dress

0.77

 isInitialized

0.75

pyplot

0.75

 Hooker

0.74

 Wray

0.73

 Tension

0.72

 DbSet

0.72

 Hooks

0.72

Activations Density 0.079%

terms associated with violence and aggressive behavior

No Comments

No Known Activations