INDEX

Explanations

occurrences of opening parentheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Se

-0.77

Es

-0.72

Tro

-0.68

mentos

-0.64

 Morales

-0.63

aphthalene

-0.63

tro

-0.63

 Turner

-0.63

-0.62

POSITIVE LOGITS

 Monfieur

1.60

 Theſe

1.57

 Houſe

1.56

Efq

1.52

 Diſ

1.50

 itſelf

1.44

 Majefty

1.42

 Reſ

1.40

 Cæsar

1.40

 Anſ

1.37

Activations Density 0.389%

occurrences of opening parentheses

No Comments

No Known Activations