INDEX

Explanations

scientific notation and references to figures or tables

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

Letters in parentheses

np_acts-logits-general · gemini-2.0-flash

figure references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Still

-0.45

Still

-0.41

 operativos

-0.41

-0.40

 still

-0.39

 enkelt

-0.39

 betrieben

-0.39

 Texto

-0.37

 coppia

-0.37

 őket

-0.36

POSITIVE LOGITS



0.93

CppMethod

0.90

Portály

0.89

 typelib

0.88

 مرئيه

0.88

ResumeLayout

0.87

 NSCoder

0.86

 <<<<<<<<<<<<<<

0.84

elemField

0.84

ViewFeatures

0.83

Activations Density 0.221%

scientific notation and references to figures or tables

Letters in parentheses

figure references

No Comments

No Known Activations