INDEX

Explanations

numerical data related to medical treatments and outcomes

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

figure references

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

SourceChecksum

-0.91

ScopeManager

-0.90

SharedCtor

-0.78

httphttps

-0.77

 ModelExpression

-0.75

ConstraintMaker

-0.75

principalColumn

-0.72

تقاوى

-0.72

 Chwiliwch

-0.71

SequentialGroup

-0.69

POSITIVE LOGITS

0.42

0.41

sm

0.41

0.40

0.38

بری

0.38

0.37

 Dickerson

0.36

Sab

0.36

Activations Density 0.028%

numerical data related to medical treatments and outcomes

figure references

No Comments

No Known Activations