INDEX

Explanations

technical terms and error codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 ateş

-0.42

SupportActionBar

-0.41

<eos>

-0.38

 huden

-0.35

ťa

-0.33

 Geist

-0.33

 مرگ

-0.32

感を

-0.32

POSITIVE LOGITS

+#+

1.24

 nahilalakip

1.04

sidemargin

1.02

richTextPanel

1.00

VersionUID

1.00

 disambiguazione

0.97

 protoimpl

0.97

enumi

0.96

unmodifiable

0.94

RetentionPolicy

0.92

Activations Density 0.338%

technical terms and error codes

No Comments

No Known Activations