INDEX

Explanations

references to Argentine footballers and their associated clubs or teams

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Pues

-0.68

VELAND

-0.66

 Appalach

-0.65

untamiento

-0.65

 himo

-0.65

 Dayton

-0.64

 retos

-0.64

 Theodo

-0.63

 يتيمه

-0.62

 Byzantium

-0.61

POSITIVE LOGITS

 Argentina

1.06

 Argent

1.03

 Argentine

1.02

 Buenos

0.97

 argent

0.90

Argentina

0.88

Argentine

0.82

Argent

0.81

 Kirchner

0.72

argentina

0.69

Activations Density 0.108%

references to Argentine footballers and their associated clubs or teams

No Comments

No Known Activations