INDEX

Explanations

bracketed mathematical expressions or 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 onCreateView

-0.59

Controllers

-0.51

hikari

-0.50

KHz

-0.48

енча

-0.48

ništvo

-0.47

chtest

-0.46

crumbs

-0.46

vedev

-0.45

//

-0.45

POSITIVE LOGITS

帖最后由

0.70

CodeAttribute

0.68

EndContext

0.67

CppMethod

0.65

 ویکی‌پدی

0.63

ThroughAttribute

0.62

GraphicsUnit

0.62

Véxase

0.61

 autorytatywna

0.60

-------------</

0.57

Activations Density 1.524%

bracketed mathematical expressions or references

No Comments

No Known Activations