INDEX

Explanations

elements related to verification tokens and event messaging in programming contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

StructEnd

-0.78

 Wikimedijinoj

-0.69

InitVars

-0.68

 Paglinawan

-0.67

CppMethod

-0.62

TypedDataSet

-0.62

 насељу

-0.61

RegressionTest

-0.60

 Augsburg

-0.59

+#+#

-0.59

POSITIVE LOGITS

csolódó

0.46

 embed

0.43

ichord

0.42

 reply

0.41

ołnier

0.41

Men

0.41

ुरु

0.41

 iParam

0.41

szönöm

0.40

例文帳に追加

0.40

Activations Density 0.077%

elements related to verification tokens and event messaging in programming contexts

No Comments

No Known Activations