INDEX

Explanations

mathematical equations and notations involving variables and operators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

}{*}{

-0.77

<td>

-0.61

migrationBuilder

-0.58

 tartalomajánló

-0.58

<th>

-0.55

 ProtoMessage

-0.54

↵↵

-0.54

<eos>

-0.52

(!__

-0.50

RegressionTest

-0.50

POSITIVE LOGITS

GEBURTS

0.78

wußt

0.68

 بيها

0.67

σθαι

0.66

 Shakspeare

0.61

öfe

0.61

apunov

0.59

 trouverez

0.58

antMatchers

0.57

 Apare

0.57

Activations Density 0.465%

mathematical equations and notations involving variables and operators

No Comments

No Known Activations