INDEX

Explanations

coding errors or exceptions related to module configuration

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Code related to error handling or exceptions

np_acts-logits-general · gemini-2.0-flash

exception handling in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Negative Logits

len

-0.73

len

-0.70

 foon

-0.65

'>{

-0.65

-0.62

">{

-0.61

-0.60

 $\{$

-0.59

Välislingid

-0.59

Efq

-0.59

POSITIVE LOGITS

 AssemblyCulture

0.70

Obrázky

0.59

:✨

0.59

localctx

0.57

0.53

ConstraintMaker

0.52

 resourceCulture

0.50

def

0.48

 Sleeps

0.48

Activations Density 0.117%

coding errors or exceptions related to module configuration

Code related to error handling or exceptions

exception handling in code

No Known Activations