INDEX

Explanations

references to filtering processes or filters in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

SequentialGroup

-0.89

onedDateTime

-0.80

 تضيفلها

-0.70

ymce

-0.70

 debout

-0.69

arakhand

-0.68

doPost

-0.66

 ReactDOM

-0.66

awtextra

-0.66

initComponents

-0.65

POSITIVE LOGITS

 filter

4.84

 filters

4.39

 Filter

4.36

filter

4.04

 Filters

3.98

Filter

3.91

 FILTER

3.84

 filtering

3.65

filters

3.40

FILTER

3.40

Activations Density 0.060%

references to filtering processes or filters in various contexts

No Comments

No Known Activations