INDEX

Explanations

phrases related to familiarity and adaptation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 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

PYX

-0.54

 propOrder

-0.50

 Roskov

-0.43

 ब्रेकडाउन

-0.43

 oprot

-0.42

 kiin

-0.38

isamment

-0.38

 ejecutivo

-0.38

 investis

-0.38

 érde

-0.38

POSITIVE LOGITS

 tolerate

0.81

 tolerance

0.78

 accustomed

0.76

 habitu

0.74

 Tolerance

0.74

 toler

0.73

习惯

0.73

Tolerance

0.70

 acost

0.66

 привы

0.66

Activations Density 0.274%

phrases related to familiarity and adaptation

No Comments

No Known Activations