INDEX

Explanations

references to specific areas or fields of study

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

beck

-0.48

 time

-0.48

-0.47

ribu

-0.46

 times

-0.45

per

-0.44

 Tremb

-0.43

emb

-0.43

POSITIVE LOGITS

 specialties

1.02

ValueStyle

0.97

 areas

0.96

 specialize

0.95

 fields

0.95

 domaines

0.93

 bidang

0.92

 Bereichen

0.92

 Areas

0.91

 specialise

0.91

Activations Density 0.218%

references to specific areas or fields of study

No Comments

No Known Activations