INDEX

Explanations

characters often associated with print statements or output in programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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



-0.68

__":

-0.67

<",

-0.66

 ComVisible

-0.63

 newBuilder

-0.62

RetentionPolicy

-0.62

 onOptions

-0.62

initComponents

-0.59

jsonwebtoken

-0.58

createCanvas

-0.57

POSITIVE LOGITS

enderror

0.71

 stund

0.59

γή

0.56

อง

0.54

abia

0.54

mare

0.53

よう

0.52

vdots

0.52

 какая

0.52

 Κυ

0.51

Activations Density 0.065%

characters often associated with print statements or output in programming languages

No Comments

No Known Activations