INDEX

Explanations

references to procedural steps or instructions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

্ষ

-0.44

 Abonnez

-0.43

 decryption

-0.42

 THEOREM

-0.42

 esterno

-0.42

Denomin

-0.40

kreuz

-0.40

 Paglinawan

-0.39

㎍

-0.38

 financière

-0.38

POSITIVE LOGITS

UnusedPrivate

0.90

BeginContext

0.85

principalColumn

0.84

GEBURTSDATUM

0.83

findpost

0.83

 مرئيه

0.80

migrationBuilder

0.80

AndEndTag

0.78

èdia

0.77

Personensuche

0.76

Activations Density 0.193%

references to procedural steps or instructions

No Comments

No Known Activations