INDEX

Explanations

programming-related code structures and keywords, particularly function definitions and method signatures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 فريبيس

-0.67

 choses

-0.59

 Roskov

-0.56

。“

-0.55

"";

-0.52

 مرئيه

-0.51

interopRequire

-0.50

 createState

-0.50

]."

-0.49

“

-0.49

POSITIVE LOGITS

final

1.31

 final

1.10

int

0.91

const

0.85

boolean

0.83

int

0.77

long

0.73

inout

0.72

string

0.71

bool

0.71

Activations Density 0.086%

programming-related code structures and keywords, particularly function definitions and method signatures

No Comments

No Known Activations