INDEX

Explanations

references to properties and configuration options in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

Who

-0.49

antik

-0.47

iettes

-0.47

といけない

-0.46

 Plan

-0.45

-0.44

The

-0.43

Cup

-0.43

limsy

-0.42

<eos>

-0.42

POSITIVE LOGITS

 فريبيس

1.01

GEBURTSDATUM

0.94

 CreateTagHelper

0.94

 transfieras

0.92

 Италијани

0.86

RenderAtEndOf

0.84

 صوتيه

0.83

发表于

0.82

StoryboardSegue

0.80

 noDo

0.77

Activations Density 0.288%

references to properties and configuration options in programming contexts

No Comments

No Known Activations