INDEX

Explanations

questions and conditional statements related to requirements and criteria

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

lamabad

-0.67

SourceChecksum

-0.64

цезда

-0.59

SequentialGroup

-0.57

makeText

-0.56

 архивлан

-0.55

 Créez

-0.55

</caption>

-0.54

lloworld

-0.54

 hObject

-0.53

POSITIVE LOGITS

 does

2.43

 Does

2.43

Does

2.35

did

2.25

Did

2.13

Did

2.02

does

1.95

Are

1.88

did

1.84

Are

1.79

Activations Density 1.407%

questions and conditional statements related to requirements and criteria

No Comments

No Known Activations