INDEX

Explanations

programming syntax related to function definitions and calls

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

Code context: function parameters and arguments

np_acts-logits-general · gemini-2.0-flash

code structure

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

'{@

-0.63

FailureListener

-0.61

XmlAccessType

-0.61

itename

-0.58

AlterField

-0.56

*/].

-0.55

 Савезне

-0.55

elemField

-0.54

UnsafeEnabled

-0.53

RetentionPolicy

-0.53

POSITIVE LOGITS

HttpServlet

0.62

bootstrapcdn

0.57

res

0.53

res

0.52

ecin

0.52

resas

0.51

substack

0.46

RES

0.45

ForValue

0.44

ywna

0.43

Activations Density 0.104%

programming syntax related to function definitions and calls

Code context: function parameters and arguments

code structure

No Comments

No Known Activations