INDEX

Explanations

phrases indicating methods or approaches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

///</

-0.88

ThroughAttribute

-0.85

ChildScrollView

-0.82

 يتيمه

-0.77

Décès

-0.75

DotNetBar

-0.72

طني

-0.72

 Audiodateien

-0.71

 Rocha

-0.69

 oprot

-0.69

POSITIVE LOGITS

 Means

2.56

Means

2.51

 means

2.39

means

2.29

 MEANS

2.20

 mean

1.47

 Mean

1.46

MEAN

1.45

 MEAN

1.43

mean

1.38

Activations Density 0.132%

phrases indicating methods or approaches

No Comments

No Known Activations