INDEX

Explanations

technical terms related to programming and configuration settings

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

Code-related punctuation and symbols

np_acts-logits-general · gemini-2.0-flash

package, auto, self, Str, tft

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 LatLng

-0.69

+#+#

-0.62

 sockaddr

-0.61

 onPostExecute

-0.60

Javadoc

-0.59

 maxn

-0.58

jfree

-0.58

estimm

-0.58

 IndexError

-0.57

 getopt

-0.57

POSITIVE LOGITS

//

0.57

global

0.55

neurial

0.54

item

0.53

base

0.53

doc

0.51

/*

0.51

member

0.51

let

0.51

rode

0.51

Activations Density 2.079%

technical terms related to programming and configuration settings

Code-related punctuation and symbols

package, auto, self, Str, tft

No Comments

No Known Activations