INDEX

Explanations

references to specific individuals and their actions or relationships in political contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Artur

-0.80

tnt

-0.79

 schist

-0.79

Gom

-0.79

 Florentine

-0.79

 Hungarian

-0.77

ganu

-0.76

rifugal

-0.75

Hungarian

-0.75

 Dorset

-0.74

POSITIVE LOGITS

 Barrow

0.75

 Antar

0.72

 Cara

0.72

kyl

0.72

aut

0.71

Sucesor

0.71

��������

0.71

 Marcos

0.70

 Bailey

0.70

rese

0.70

Activations Density 1.623%

references to specific individuals and their actions or relationships in political contexts

No Known Activations