INDEX

Explanations

references to administrative or procedural topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 HasFactory

-0.79

برا

-0.53

脚注の使い方

-0.52

SM

-0.51

lama

-0.51

Erm

-0.51

 Hama

-0.48

UNTAIN

-0.48

Hama

-0.48

 patterns

-0.48

POSITIVE LOGITS

fjspx

1.08

 nakalista

0.96

 propOrder

0.87

 getopt

0.86

Хьажоргаш

0.77

 useAuth

0.77

endphp

0.74

knapp

0.74

 getItemId

0.74

pii

0.72

Activations Density 0.401%

references to administrative or procedural topics

No Comments

No Known Activations