INDEX

Explanations

programming-related syntax and function calls

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

Go code snippets with error handling

np_acts-logits-general · gemini-2.0-flash

Theorem, heavily, relative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

int

-0.72

httphttps

-0.66

'.

-0.64

'+

-0.60

DebuggerNonUser

-0.59

 bool

-0.59

int

-0.58

 mxArray

-0.58

 Вікіпе

-0.57

'(

-0.57

POSITIVE LOGITS

_,

1.11

_,

0.87

defer

0.84

if

0.76

var

0.71

_);

0.66

if

0.63

//

0.62

err

0.61

err

0.61

Activations Density 0.061%

programming-related syntax and function calls

Go code snippets with error handling

Theorem, heavily, relative

No Comments

No Known Activations