INDEX

Explanations

instances of "Math" and variations of related mathematical terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Theſe

-0.80

 Monfieur

-0.73

 Houſe

-0.71

 ſeveral

-0.69

 preſent

-0.68

SCRIBE

-0.68

 fevere

-0.67

 Diſ

-0.67

 Reſ

-0.66

 poffible

-0.66

POSITIVE LOGITS

St

1.28

Dr

1.10

St

1.08

Dr

0.89

Ms

0.87

Fr

0.85

 Math

0.84

Math

0.82

Ma

0.72

 Blvd

0.72

Activations Density 0.093%

instances of "Math" and variations of related mathematical terminology

No Comments

No Known Activations