INDEX

Explanations

patterns or references to programming or coding structures in the text

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

Code snippets or file paths

np_acts-logits-general · gemini-2.0-flash

technical questions and code snippets

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

LookAnd

-0.75

Vidite

-0.57

↵↵

-0.54

webElementXpaths

-0.53

 Cooley

-0.53

-0.51

คัญ

-0.47

jsii

-0.46

apollo

-0.46

Над

-0.46

POSITIVE LOGITS

ContentAsync

0.76

findpost

0.75

 kasarigan

0.73

PyExc

0.72

istoitu

0.71

enumi

0.71

 Audiodateien

0.68

 leſs

0.67

AddTagHelper

0.67

tagHelperRunner

0.66

Activations Density 0.007%

patterns or references to programming or coding structures in the text

Code snippets or file paths

technical questions and code snippets

No Comments

No Known Activations