INDEX

Explanations

sections of code that indicate the structure and formatting of data or UI elements

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

equations and code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

VolleyError

-0.57

BufferException

-0.56

 ब्रेकडाउन

-0.56

 MainAxisSize

-0.53

niająca

-0.53

AutoScaleMode

-0.52

didSet

-0.52

ModelSerializer

-0.52

IBOutlet

-0.51

onOptions

-0.51

POSITIVE LOGITS

<eos>

0.47

DockStyle

0.39

 gynhyrchwyd

0.38

 Diret

0.35

Dependencies

0.34

➋

0.34

 colher

0.33

AndEndTag

0.32

 noDo

0.32

Deps

0.32

Activations Density 0.011%

sections of code that indicate the structure and formatting of data or UI elements

equations and code snippets

No Comments

No Known Activations