INDEX

Explanations

references to specific numerical identifiers or titles associated with cultural works

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

Sucesor

-0.69

Portale

-0.68

—

-0.67

 препратки

-0.62

GEBURTS

-0.61

getDescriptor

-0.60

 يتيمه

-0.59

 propOrder

-0.59

UnusedPrivate

-0.59

OrBuilder

-0.59

POSITIVE LOGITS

 EconPapers

0.57

CWE

0.54

 Seven

0.52

setViewName

0.51

uzen

0.50

Seven

0.50

Nine

0.49

 Five

0.48

Five

0.47

 Four

0.46

Activations Density 0.163%

references to specific numerical identifiers or titles associated with cultural works

No Comments

No Known Activations