INDEX

Explanations

function calls and expressions in code

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

error handling

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

Tikang

-0.74

хьтан

-0.64

UserScript

-0.62

'{@

-0.60

rungsseite

-0.60

Jeografia

-0.59

Ƚ

-0.56

delwed

-0.56

 виправивши

-0.55

تقاوى

-0.54

POSITIVE LOGITS

catchError

0.53

FailureListener

0.51

printStackTrace

0.45

 problems

0.45

ală

0.41

 errors

0.40

 difficulties

0.40

NSError

0.39

VolleyError

0.39

 error

0.38

Activations Density 0.001%

function calls and expressions in code

error handling

No Comments

No Known Activations