INDEX

Explanations

terms related to visual elements or visual representation

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

PropertyChanging

-0.56

RegressionTest

-0.55

flik

-0.51

mar

-0.51

mybatisplus

-0.48

Ow

-0.47

readystatechange

-0.47

👦

-0.46

eventbus

-0.46

InitStruct

-0.45

POSITIVE LOGITS

 visual

2.01

 Visual

2.00

Visual

1.94

visual

1.84

 VISUAL

1.83

VISUAL

1.72

 visualisation

1.67

 visualize

1.65

 visualized

1.58

 visualization

1.56

Activations Density 0.110%

terms related to visual elements or visual representation

No Comments

No Known Activations