INDEX

Explanations

import statements for data manipulation and visualization libraries in Python

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nakalista

-0.80

CreateModel

-0.79

))).

-0.74

)))),

-0.73

 <<<<<<<<<<<<<<

-0.71

endregion

-0.69

))),

-0.69

svet

-0.68

 Blen

-0.67

))){

-0.66

POSITIVE LOGITS

 numpy

1.45

numpy

1.03

Pyx

0.91

 GenerationType

0.91

MessageTagHelper

0.88

pyplot

0.76

 InputDecoration

0.73

HasAnnotation

0.67

 jPanel

0.67

 pandas

0.66

Activations Density 0.003%

import statements for data manipulation and visualization libraries in Python

No Comments

No Known Activations