INDEX

Explanations

phrases related to legal applicability and references

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Wikimedijinoj

-0.51

stdc

-0.48

 Halen

-0.46

LookAnd

-0.46

Legături

-0.45

 bề

-0.45

Koordinaten

-0.45

 Biôgrafia

-0.44

čený

-0.43

kháu

-0.43

POSITIVE LOGITS

lamabad

0.61

AndEndTag

0.61

Autoritní

0.60

 Applicability

0.54

OGND

0.54

lavia

0.53

mybatisplus

0.53

ActionCreators

0.53

StructEnd

0.53

tagHelperRunner

0.52

Activations Density 1.234%

phrases related to legal applicability and references

No Comments

No Known Activations