INDEX

Explanations

mathematical expressions and notations related to functions and accuracy

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

Mathematical/statistical deviation or tolerance

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 Roskov

-0.43

zzleHttp

-0.30

 trời

-0.29

rified

-0.27

Pot

-0.27

 chi̍t

-0.27

Pot

-0.26

koh

-0.25

GeneratedMessage

-0.25

 stroom

-0.25

POSITIVE LOGITS

 tolerances

1.27

 tolerance

1.26

 Tolerance

1.19

 deviation

1.09

 Toler

1.09

 accuracy

1.07

tolerance

1.06

 inaccuracy

1.06

Tolerance

1.05

 deviations

1.04

Activations Density 1.506%

mathematical expressions and notations related to functions and accuracy

Mathematical/statistical deviation or tolerance

No Comments

No Known Activations