INDEX

Explanations

occurrences of the word "list" and its variations in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

="#"><

-0.83

FXML

-0.80

contentLoaded

-0.76

"}";

-0.76

xodo

-0.76

SequentialGroup

-0.75

>`;

-0.74

 vPvB

-0.73

 Weih

-0.73

.$$

-0.73

POSITIVE LOGITS

list

1.01

 lifetime

0.81

 gallery

0.81

gallery

0.74

 galleries

0.72

 suite

0.71

listItem

0.70

 Suzy

0.68

 Gallery

0.67

ान्त

0.66

Activations Density 0.084%

occurrences of the word "list" and its variations in programming contexts

No Comments

No Known Activations