INDEX

Explanations

programming and error handling terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

quiti

-0.60

RTLD

-0.50

 substan

-0.48

 agrí

-0.46

++){

-0.46

Jîn

-0.45

生ま

-0.45

 idén

-0.44

 escol

-0.43

 inoxid

-0.43

POSITIVE LOGITS

SequentialGroup

0.98

 يتيمه

0.93

EndInit

0.85

MigrationBuilder

0.81

 Puzzles

0.78

printStackTrace

0.78

DockStyle

0.74

 puzzle

0.72

 puzzles

0.71

+#+#

0.70

Activations Density 2.177%

programming and error handling terms

No Comments

No Known Activations