INDEX

Explanations

terms related to regulation and directional changes (up and down)

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

"Up" or "Down" as an indicator of direction

np_acts-logits-general · gemini-2.0-flash

up or down states and direction

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

RegressionTest

-0.72

DoubleQuotes

-0.66

StructEnd

-0.61

rivit

-0.60

 tala

-0.60

dafx

-0.59

drawImage

-0.58

RunAsync

-0.57

はじめに

-0.56

odymium

-0.56

POSITIVE LOGITS

 down

0.90

 Down

0.82

 DOWN

0.79

Down

0.77

down

0.74

Up

0.72

up

0.69

bitField

0.67

EndContext

0.67

databind

0.66

Activations Density 0.121%

terms related to regulation and directional changes (up and down)

"Up" or "Down" as an indicator of direction

up or down states and direction

No Comments

No Known Activations