INDEX

Explanations

numeric representations in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 مشين

-0.93

 nahilalakip

-0.86

Aiheesta

-0.84

ContentAsync

-0.84

فایل‌لار

-0.84

 архивлан

-0.83

новништво

-0.82

InstrumentedTest

-0.82

 ProtoMessage

-0.81

 referrerpolicy

-0.81

POSITIVE LOGITS

ba

0.77

ae

0.70

0.68

bb

0.68

ca

0.67

CA

0.66

da

0.66

cb

0.65

Activations Density 1.822%

numeric representations in a structured format

No Comments

No Known Activations