INDEX

Explanations

programming function definitions

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

API request methods

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

 Krum

-0.53

ColumnIndex

-0.53

 Rasmussen

-0.50

 carbons

-0.48

ariums

-0.47

Silicon

-0.46

FromArray

-0.46

 Silicon

-0.46

<h2>

-0.44

 Baumann

-0.44

POSITIVE LOGITS

 doGet

2.61

doGet

1.44

 doPost

1.22

tagHelperRunner

0.68

GetMapping

0.60

StructEnd

0.57

HttpGet

0.53

 onOptions

0.50

WithIOException

0.45

 testGet

0.45

Activations Density 0.000%

programming function definitions

API request methods

No Comments

No Known Activations