INDEX

Explanations

phone numbers and related numerical information

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 taken

-0.55

batim

-0.54

shed

-0.54

 estekak

-0.51

esac

-0.50

NOPQRST

-0.48

COLN

-0.48

 Basic

-0.47

Basic

-0.47

scala

-0.46

POSITIVE LOGITS

invokeLater

0.90

DockStyle

0.85

 Shakspeare

0.61

 ISNI

0.59

 electrification

0.59

WithMany

0.59

 consultato

0.58

 HARRISON

0.58

 rivista

0.58

XE

0.57

Activations Density 0.119%

phone numbers and related numerical information

No Comments

No Known Activations