INDEX

Explanations

legal terminology and case-related terminology

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

expandindo

-0.75

 NgModule

-0.75

ThroughAttribute

-0.74

 tartalomajánló

-0.72

WriteBarrier

-0.68

 propOrder

-0.67

 EconPapers

-0.66

Bronnen

-0.66

脚注の使い方

-0.65

 mergeFrom

-0.64

POSITIVE LOGITS

</em>

0.62

</i>

0.53

IsContent

0.51

 resourceCulture

0.48

UnusedPrivate

0.48

enn

0.48

 ligação

0.47

0.45

RenderAtEndOf

0.44

ыгана

0.43

Activations Density 1.147%

legal terminology and case-related terminology

No Comments

No Known Activations