INDEX

Explanations

instances of the word "char" or related 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 @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Enoch

-0.85

PX

-0.84

óbal

-0.81

 Multip

-0.79

venido

-0.77

 Oppen

-0.76

 Petrov

-0.75

typeparam

-0.74

 Goliath

-0.74

LikeLike

-0.73

POSITIVE LOGITS

 Char

1.32

 CHAR

1.29

 charts

1.27

 char

1.22

CHAR

1.21

 Charts

1.19

Char

1.18

 Charlene

1.18

 chars

1.14

 chart

1.07

Activations Density 0.067%

instances of the word "char" or related variations in programming contexts

No Comments

No Known Activations