INDEX

Explanations

programming syntax and structure elements, particularly related to function definitions and condition checks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-1.05

 myſelf

-0.95

 ―――――

-0.94

 ་་

-0.90

 ainfi

-0.89

Efq

-0.87

 CommonModule

-0.83

 doubtnut

-0.83

 ſtate

-0.83

 auffi

-0.82

POSITIVE LOGITS

principalTable

0.58

↵↵

0.56

0.53

val

0.51

<?

0.49

0.48

ph

0.47

Activations Density 0.788%

programming syntax and structure elements, particularly related to function definitions and condition checks

No Comments

No Known Activations