INDEX

Explanations

references to Java classes and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

InjectAttribute

-0.89

 protoimpl

-0.84

MigrationBuilder

-0.78

ThroughAttribute

-0.67

tonsoft

-0.62

IndentedString

-0.61

ContentAsync

-0.60

hoeddwyd

-0.59

 SQLAlchemy

-0.59

 Bergh

-0.58

POSITIVE LOGITS

sun

0.72

sun

0.64

//$

0.59

 java

0.55

Sun

0.54

Sun

0.54

beans

0.52

 applet

0.50

 Suns

0.50

JNI

0.48

Activations Density 0.778%

references to Java classes and documentation

No Comments

No Known Activations