INDEX

Explanations

terms related to legal proceedings and clinical research

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

lső

-0.49

 flag

-0.44

 general

-0.43

rec

-0.43

pit

-0.42

 Seeder

-0.42

mallows

-0.41

 surla

-0.41

 layar

-0.41

 said

-0.40

POSITIVE LOGITS

ImageContext

0.92

CppCodeGen

0.84

 MessageBoxIcon

0.83

GraphicsUnit

0.79

oredCriteria

0.78

PyExc

0.72

 kasarigan

0.69

TintMode

0.68

 '\\;'

0.68

UnusedPrivate

0.68

Activations Density 0.424%

terms related to legal proceedings and clinical research

No Comments

No Known Activations