INDEX

Explanations

numeric values and variables relevant to programming or data structures

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

 milliers

-0.54

 <<<<<<<<<<<<<<

-0.51

utilisons

-0.49

Handlung

-0.48

 لد

-0.48

 facilité

-0.48

werd

-0.46

 việt

-0.46

 Komun

-0.45

 chaine

-0.45

POSITIVE LOGITS

 يتيمه

0.77

GraphicsUnit

0.61

ellite

0.59

FormTagHelper

0.57

 intptr

0.56

AxisAlignment

0.56

InvalidProtocol

0.54

)))));

0.54

 pylint

0.53

ftype

0.53

Activations Density 0.376%

numeric values and variables relevant to programming or data structures

No Comments

No Known Activations