INDEX

Explanations

structures related to logical or mathematical comparisons

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

-0.49

 isInitialized

-0.44

 AssemblyCulture

-0.43

 preocupes

-0.42

Se

-0.41

ten

-0.41

共

-0.40

 hacerte

-0.40

RegistryLite

-0.39

oucí

-0.38

POSITIVE LOGITS

sidemargin

0.90

 tartalomajánló

0.88

 >=",

0.83

 itſelf

0.83

Efq

0.81

 fhort

0.79

MemoryWarning

0.78

 Shakspeare

0.76

 ſta

0.76

 Monfieur

0.74

Activations Density 1.279%

structures related to logical or mathematical comparisons

No Comments

No Known Activations