INDEX

Explanations

references to programming imports and libraries related to JSON processing

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

import statements

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 GetEnumerator

-0.49

TextHelper

-0.45

kter

-0.43

 دع

-0.42

 enseñ

-0.42

tikum

-0.41

 campana

-0.40

ỳ

-0.40

 kasarigan

-0.40

Cater

-0.40

POSITIVE LOGITS

RenderAtEndOf

0.71

tonsoft

0.65

WireFormatLite

0.63

PerformLayout

0.61

Zitat

0.59

 forState

0.59

leap

0.59

zeba

0.59

angeran

0.59

sidemargin

0.57

Activations Density 0.011%

references to programming imports and libraries related to JSON processing

import statements

No Comments

No Known Activations