INDEX

Explanations

comparisons of assumptions related to statistical models

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

"weaker" or "stronger"

np_acts-logits-general · gemini-2.0-flash

weaker than, stronger than

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

RRect

-0.56

 gelungen

-0.52

ndice

-0.51

HandlerContext

-0.51

 समीक्षाओं

-0.48

 chronique

-0.48

 geschafft

-0.48

chuhe

-0.48

 XCTest

-0.48

InjectAttribute

-0.47

POSITIVE LOGITS

 minimal

0.72

 scope

0.71

 minimum

0.68

minimal

0.64

 minimale

0.64

 maximal

0.62

 Expanded

0.62

level

0.62

 downgrade

0.62

 scopes

0.61

Activations Density 0.743%

comparisons of assumptions related to statistical models

"weaker" or "stronger"

weaker than, stronger than

No Comments

No Known Activations