INDEX

Explanations

references to the current instance or context within a code structure

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

self or this in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 pleaſure

-0.61

inWeight

-0.56

 ſever

-0.55

 queſta

-0.55

 ſta

-0.52

 purpoſe

-0.52

 raiſ

-0.51

 IOError

-0.51

wpi

-0.50

SequentialGroup

-0.50

POSITIVE LOGITS

 appelez

0.40

This

0.39

omitempty

0.39

Espèce

0.38

RTSN

0.38

 THIS

0.37

beforeEach

0.37

 this

0.36

 bele

0.36

staticmethod

0.36

Activations Density 0.003%

references to the current instance or context within a code structure

self or this in code

No Comments

No Known Activations