INDEX

Explanations

phrases indicating conditions or possibilities, often in a hypothetical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Efq

-1.05

^(@)

-0.82

 Monfieur

-0.81

 myſelf

-0.78

 Saltar

-0.77

 Theſe

-0.76

 houſe

-0.75

 Houſe

-0.73

Bronnen

-0.72

 iſt

-0.71

POSITIVE LOGITS

tagext

0.59

</blockquote>

0.56

<eos>

0.55

↵↵↵

0.52

why

0.50

↵

0.50

cuadro

0.49

↵↵

0.49

rawDesc

0.46

so

0.45

Activations Density 1.359%

phrases indicating conditions or possibilities, often in a hypothetical context

No Comments

No Known Activations