INDEX

Explanations

affirmations of well-being or acceptance

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

^(@)

-0.90

 ་་

-0.84

 Shakspeare

-0.84

PreferredItem

-0.83

 itſelf

-0.81

ſelf

-0.79

abestanden

-0.77

SourceChecksum

-0.75

 ―――――

-0.74

)";

-0.73

POSITIVE LOGITS

ok

1.09

 okay

0.79

OK

0.74

ok

0.73

თ

0.61

 bizony

0.56

 please

0.56

 réf

0.54

 grazia

0.54

opha

0.53

Activations Density 0.090%

affirmations of well-being or acceptance

No Comments

No Known Activations