INDEX

Explanations

function-related terms and keywords in code

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

Code or data processing-related terms

np_acts-logits-general · gemini-2.0-flash

function calls with arguments

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.70

-0.69

-0.65

co

-0.64

-0.63

ob

-0.60

un

-0.60

-0.59

go

-0.59

POSITIVE LOGITS

 pleaſure

1.27

 Houſe

1.22

 Majefty

1.18

Efq

1.17

 Jefus

1.17

 Monfieur

1.16

 purpoſe

1.16

 Reſ

1.16

 myſelf

1.14

 ſche

1.13

Activations Density 0.427%

function-related terms and keywords in code

Code or data processing-related terms

function calls with arguments

No Comments

No Known Activations