INDEX

Explanations

programming language syntax and related structures

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

Code snippets, especially related to shading or metrics

np_acts-logits-general · gemini-2.0-flash

wire or TAB bonding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

-0.67

；

-0.66

__;

-0.57

”;

-0.54

*/;

-0.54

 sẻ

-0.54

*;

-0.53

’;

-0.51

.;

-0.51

-0.50

POSITIVE LOGITS

!=

0.80

!==

0.77

리가

0.74

hasOwnProperty

0.73

isn

0.69

==

0.68

__(/*!

0.67

 wasn

0.67

")==

0.64

 DbType

0.64

Activations Density 0.186%

programming language syntax and related structures

Code snippets, especially related to shading or metrics

wire or TAB bonding

No Comments

No Known Activations