INDEX

Explanations

the presence of programming-related terminology and function definitions

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

Code-related tokens and programming terms

np_acts-logits-general · gemini-2.0-flash

creating code snippets

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 conmigo

-0.87

 comigo

-0.82

 femei

-0.72

 addirittura

-0.69

 thence

-0.68

 storici

-0.67

oredCriteria

-0.67

 griega

-0.67

 nicio

-0.66

 fVar

-0.65

POSITIVE LOGITS

 list

0.87

our

0.80

all

0.80

 main

0.78

the

0.77

 basic

0.73

")){

0.73

 current

0.73

 array

0.72

 info

0.70

Activations Density 0.248%

the presence of programming-related terminology and function definitions

Code-related tokens and programming terms

creating code snippets

No Comments

No Known Activations