INDEX

Explanations

programming-related keywords and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

-0.84

<eos>

-0.59

-0.51

 pulang

-0.48

↵

-0.46

-0.45

<strong>

-0.42

-0.40

an

-0.39

POSITIVE LOGITS

 betweenstory

1.36

ViewFeatures

1.22

GEBURTSDATUM

1.16

awtextra

1.10

 nahilalakip

1.08

 Chwiliwch

1.07

ScopeManager

1.06

tvguidetime

1.05

onViewCreated

1.04

UIControlState

1.03

Activations Density 1.265%

programming-related keywords and identifiers

No Comments

No Known Activations