INDEX

Explanations

references to code and coding terminology

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

enschappelijke

-0.73

клопе

-0.68

__":

-0.67

 يتيمه

-0.64

 GenerationType

-0.62

iconque

-0.62

 []),

-0.61

"],

-0.60

 ligiloj

-0.60

()");

-0.60

POSITIVE LOGITS

 code

4.16

 Code

3.98

Code

3.97

code

3.88

 CODE

3.58

CODE

3.50

 codes

3.21

 Codes

3.06

codes

2.88

 código

2.78

Activations Density 0.094%

references to code and coding terminology

No Comments

No Known Activations