INDEX

Explanations

specific identifiers and statistics related to various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

GEBURTSDATUM

-1.12

complexContent

-0.78

GenerationType

-0.78

 виправивши

-0.77

IUrlHelper

-0.77



-0.75

initComponents

-0.74

 Савезне

-0.74

IntoConstraints

-0.74

الإنجليزية

-0.73

POSITIVE LOGITS

is

0.67

 will

0.59

ref

0.54

 infatti

0.49

 must

0.48

can

0.48

은

0.47

"]').

0.47

ização

0.46

lot

0.46

Activations Density 0.541%

specific identifiers and statistics related to various subjects

No Comments

No Known Activations