INDEX

Explanations

terms indicating size or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Geplaatst

-0.95

BagConstraints

-0.71

UrlResolution

-0.69

 <<<<<<<<<<<<<<

-0.69

ImageContext

-0.67

 judiciales

-0.67

 getopt

-0.66

aarrggbb

-0.65

hésite

-0.65

EndGlobalSection

-0.63

POSITIVE LOGITS

 large

3.69

large

3.26

Large

3.04

big

3.04

 Large

2.96

 LARGE

2.82

 grandes

2.78

 grote

2.76

 grande

2.67

 großen

2.63

Activations Density 0.177%

terms indicating size or significance

No Comments

No Known Activations