INDEX

Explanations

references to proteins and their associated data in scientific contexts

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

protein activation pathways and Greek letters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<h1>

-0.40

CGRect

-0.37

dorf

-0.32

NSUInteger

-0.30

doras

-0.29

IANGLES

-0.29

bis

-0.28

 drastically

-0.28

Product

-0.28

–

-0.28

POSITIVE LOGITS

PerformLayout

0.67

fjspx

0.67

AddTagHelper

0.64

WithIOException

0.60

TagMode

0.60

 GenerationType

0.60

ftagPool

0.59

 Bioaccumulative

0.59

 Савезне

0.58

Cursors

0.58

Activations Density 0.202%

references to proteins and their associated data in scientific contexts

protein activation pathways and Greek letters

No Comments

No Known Activations