INDEX

Explanations

mentions of specific names and identifiers related to characters or subjects in a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Vidite

-0.76

 pitié

-0.71

 licorne

-0.67

 coloriage

-0.66

 CONDUIT

-0.65

 colère

-0.64

 BORROW

-0.63

 vétérina

-0.62

ukup

-0.59

 NAVY

-0.58

POSITIVE LOGITS

 estekak

0.73

 كومونز

0.71

ThroughAttribute

0.67

abestanden

0.65

 незавершена

0.65

 GenerationType

0.64

 ComVisible

0.60

новништво

0.59

autoconfigure

0.59

ルト

0.57

Activations Density 0.113%

mentions of specific names and identifiers related to characters or subjects in a narrative

No Comments

No Known Activations