INDEX

Explanations

structures associated with mathematical or logical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Signalez

-0.64

InputBorder

-0.59

swire

-0.55

tudo

-0.48

 AssemblyProduct

-0.44

Either

-0.43

this

-0.42

Enders

-0.42

riceps

-0.42

既

-0.41

POSITIVE LOGITS

それに

0.77

存于互联网档案馆

0.76

ndash

0.74

CppMethod

0.69

 alike

0.68

antiate

0.68

 Италијани

0.67

 GenerationType

0.66

žen

0.64

 sundry

0.63

Activations Density 0.732%

structures associated with mathematical or logical expressions

No Comments

No Known Activations