INDEX

Explanations

largest entities or notable achievements within a specified context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 незавершена

-0.90

AccessorTable

-0.90

principalTable

-0.87

ArgsConstructor

-0.86

ItemBackground

-0.79

 Audiodateien

-0.79

tagHelperRunner

-0.78

 estekak

-0.73

RetentionPolicy

-0.73

}\]

-0.72

POSITIVE LOGITS

 widest

0.57

la

0.49

 ever

0.48

üne

0.46

®

0.45

roslav

0.45

 open

0.44

 broadest

0.44

Activations Density 0.272%

largest entities or notable achievements within a specified context

No Comments

No Known Activations