INDEX

Explanations

error handling and notification structures in code

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

Code snippets or references

np_acts-logits-general · gemini-2.0-flash

energy needs, studies indicate

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

StoryboardSegue

-0.80

 rhestr

-0.65

 negozi

-0.64

principalTable

-0.62

 ExecuteAsync

-0.57

 članak

-0.56

 IBOutlet

-0.54

Viitteet

-0.53

 HasFactory

-0.53

JsonPropertyName

-0.52

POSITIVE LOGITS

tagHelper

0.56

 Italijanski

0.54

 dame

0.52

 Sticks

0.52

 Krá

0.51

phosa

0.51

ritic

0.51

 vVar

0.51

 Timeless

0.50

 brioche

0.50

Activations Density 0.138%

error handling and notification structures in code

Code snippets or references

energy needs, studies indicate

No Comments

No Known Activations