INDEX

Explanations

terms related to programming errors and debugging in code

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

Web-related configuration files and code snippets

np_acts-logits-general · gemini-2.0-flash

web server files and code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 représentants

-0.64

RTDA

-0.64

>//

-0.63

complexType

-0.60

copyWith

-0.58

 professeurs

-0.58

 habet

-0.58

 quoque

-0.57

coroutines

-0.56

 kılıf

-0.54

POSITIVE LOGITS

web

0.66

CGI

0.60

 HTML

0.60

web

0.58

 visitors

0.57

 visitor

0.56

CSRF

0.56

cgi

0.55

<%@

0.55

 admin

0.55

Activations Density 1.098%

terms related to programming errors and debugging in code

Web-related configuration files and code snippets

web server files and code

No Comments

No Known Activations