INDEX

Explanations

questions and statements related to inquiries or requests for information

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

Followed by a question

np_acts-logits-general · gemini-2.0-flash

questions starting with who what how

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

LookAnd

-0.88

Personensuche

-0.73

MigrationBuilder

-0.66

WebVitals

-0.64

Mereka

-0.63

alnız

-0.61

agus

-0.60

حياتها

-0.60

wegg

-0.59

anskje

-0.58

POSITIVE LOGITS

 What

1.73

What

1.52

How

1.41

How

1.23

 Which

1.22

 Where

1.21

Who

1.18

Where

1.08

Which

1.04

Who

1.04

Activations Density 0.227%

questions and statements related to inquiries or requests for information

Followed by a question

questions starting with who what how

No Comments

No Known Activations