INDEX

Explanations

database-related actions and keywords

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

legal citations and database commands

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

CppMethod

-0.77

 queſta

-0.63

 Weiſe

-0.62

[@BOS@]

-0.61

<unused14>

-0.61

<unused40>

-0.61

<unused41>

-0.61

<unused28>

-0.61

<pad>

-0.61

<unused3>

-0.61

POSITIVE LOGITS

executeUpdate

1.98

ExecuteNonQuery

1.27

NonQuery

0.59

SaveChangesAsync

0.45

ActionPerformed

0.44

execute

0.41

 Execute

0.40

VYMaps

0.39

Execute

0.39

 executed

0.36

Activations Density 0.000%

database-related actions and keywords

legal citations and database commands

No Comments

No Known Activations