INDEX

Explanations

references to talent and skill in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Checkpoint

-0.66

 يتيمه

-0.64

govine

-0.63

 surla

-0.61

 sopa

-0.60

checker

-0.58

frame

-0.58

 Checker

-0.57

MigrationBuilder

-0.57

+#+

-0.57

POSITIVE LOGITS

 talent

3.15

talent

2.79

 Talent

2.78

Talent

2.69

 talents

2.63

 Talents

2.41

 talento

2.15

 talentos

2.15

 talented

2.15

 талан

1.73

Activations Density 0.070%

references to talent and skill in various contexts

No Comments

No Known Activations