INDEX

Explanations

programming-related keywords and function definitions

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

Code, PDB, or database entries

np_acts-logits-general · gemini-2.0-flash

entering or entry

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

 resourceCulture

-0.70

styleable

-0.63

 Signalez

-0.59

RTDA

-0.59

IUrlHelper

-0.58

Демографія

-0.55

/**

-0.55

ьаж

-0.54

SizeF

-0.53

dafx

-0.53

POSITIVE LOGITS

 entry

4.04

 Entry

3.61

entry

3.58

Entry

3.38

 ENTRY

3.23

 entering

3.11

 entered

3.05

 entries

3.04

 enter

3.00

 enters

2.99

Activations Density 0.377%

programming-related keywords and function definitions

Code, PDB, or database entries

entering or entry

No Comments

No Known Activations