INDEX

Explanations

occurrences of the word "char" and variations related to character data types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 Glut

-0.78

athione

-0.77

Tikang

-0.76

="#"><

-0.76

ostante

-0.76

 Petrov

-0.75

 Timp

-0.74

📁

-0.74

 Himal

-0.72

///<

-0.72

POSITIVE LOGITS

 char

1.08

 CHAR

1.07

 Char

1.06

Char

1.03

CHAR

1.03

 chars

1.00

 Schar

0.96

char

0.90

 Charlene

0.82

chars

0.81

Activations Density 0.111%

occurrences of the word "char" and variations related to character data types

No Comments

No Known Activations