INDEX

Explanations

inquiries and requests for information or assistance regarding techniques and resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 itſelf

-0.78

mybatisplus

-0.76

 raiſ

-0.70

 purpoſe

-0.70

 myſelf

-0.69

 themſelves

-0.67

ſelf

-0.66

 unſ

-0.66

 holotype

-0.65

 pleaſure

-0.65

POSITIVE LOGITS

 please

0.61

 resourceCulture

0.60

Stuck

0.60

please

0.55

덤

0.54

 Stuck

0.54

 preferably

0.52

...

0.50

preferably

0.50

...

0.49

Activations Density 0.230%

inquiries and requests for information or assistance regarding techniques and resources

No Comments

No Known Activations