INDEX

Explanations

references to fine quality or precision in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

preduce

-0.88

 Balloons

-0.83

 Vesu

-0.82

rrggbb

-0.82

 INTERESAR

-0.81

 hObject

-0.79

นาย

-0.79

="@+

-0.77

 sclerosis

-0.76

 McCl

-0.75

POSITIVE LOGITS

FINE

1.43

 Fine

1.38

fine

1.36

Fine

1.36

 Fines

1.36

 FINE

1.33

 fine

1.27

 fines

1.22

fines

1.19

 fined

1.16

Activations Density 0.079%

references to fine quality or precision in various contexts

No Comments

No Known Activations