INDEX

Explanations

references to specific individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

UnknownFieldSet

-0.67

sstream

-0.61

InitStruct

-0.53

 مرئيه

-0.52

thâu

-0.49

 kasarigan

-0.49

 linkovi

-0.46

帖最后由

-0.44

 található

-0.43

IndentedString

-0.43

POSITIVE LOGITS

principalColumn

0.66

tvguidetime

0.64

onViewCreated

0.61

 AssemblyVersion

0.57

arakhand

0.57

prepareStatement

0.57

----</

0.57

BagConstraints

0.56

ConstraintMaker

0.56

IsPostBack

0.56

Activations Density 1.027%

references to specific individuals or entities

No Comments

No Known Activations