INDEX

Explanations

references to programming constructs or error messages related to code functionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

uxxxx

-0.70

+:+

-0.64

djangoproject

-0.61

ImageIO

-0.59

NgModule

-0.59

IonicModule

-0.58

<bos>

-0.58

ServletConfig

-0.57

 WaitForSeconds

-0.56

Portail

-0.56

POSITIVE LOGITS

 "..\..\..\

0.69

MutableLiveData

0.65

 "..\..\

0.63

 ViewModel

0.59

 models

0.59

 model

0.55

ViewModel

0.52

model

0.51

PreInfinity

0.49

raging

0.49

Activations Density 0.178%

references to programming constructs or error messages related to code functionality

No Comments

No Known Activations