INDEX

Explanations

structured data inputs and index references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

RenderAtEndOf

-0.85

]<<"

-0.83

\{\\

-0.82

"""

-0.81

"];

-0.80

 كومونز

-0.77

tagHelperRunner

-0.76

reportWebVitals

-0.75

/**

-0.74

 milliards

-0.74

POSITIVE LOGITS

 position

0.56

 number

0.55

PageIndex

0.53

pos

0.53

 номер

0.53

number

0.52

 rank

0.51

index

0.50

Номер

0.50

Unione

0.49

Activations Density 0.553%

structured data inputs and index references

No Comments

No Known Activations