INDEX

Explanations

phrases and terms related to technical or legal contexts, particularly involving programming and security

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

 travaillons

-0.61

gdala

-0.54

AccessorTable

-0.53

^(@)

-0.53

CIC

-0.51

XmlAccessType

-0.50

 Molière

-0.50

 playmobil

-0.49

Grüße

-0.49

diers

-0.49

POSITIVE LOGITS

0.68

0.59

bitField

0.59

 onOptions

0.58

 CreateTagHelper

0.57

RTGC

0.54

 nakalista

0.54

enumi

0.53

허

0.52

OB

0.52

Activations Density 0.310%

phrases and terms related to technical or legal contexts, particularly involving programming and security

No Comments

No Known Activations