INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22

Prompts (Dashboard)

24,576 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

 őket

-0.55

 старости

-0.49

Snap

-0.47

REE

-0.47

LSM

-0.44

UGS

-0.43

 thought

-0.43

able

-0.43

حال

-0.43

 apă

-0.42

POSITIVE LOGITS

own

1.05

jectures

0.95

Ārējās

0.94

 &___

0.93

 AssemblyCompany

0.90

SequentialGroup

0.89

mybatisplus

0.88

WriteBarrier

0.87

AddTagHelper

0.87

}")

0.84

Activations Density 0.079%

No Comments

No Known Activations