INDEX

Explanations

references to lessons learned from experiences or failures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 AssemblyCulture

-0.66

setVerticalGroup

-0.64

setof

-0.60

VIATIONS

-0.55

styleType

-0.55

исленность

-0.55

 referenties

-0.54

EndGlobalSection

-0.53

 Roskov

-0.53

 onOptions

-0.53

POSITIVE LOGITS

 lessons

2.22

 learned

2.08

 lesson

2.04

 Lessons

1.98

 learn

1.97

 learns

1.92

 learning

1.91

learned

1.91

 learnt

1.86

lessons

1.83

Activations Density 0.343%

references to lessons learned from experiences or failures

No Comments

No Known Activations