INDEX

Explanations

references to the programming language Python and its various attributes or usages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Houſe

-0.99

 ſche

-0.93

Efq

-0.92

(;;)

-0.92

 raiſ

-0.90

 themſelves

-0.89

 ―――――

-0.87

 doubtnut

-0.86

 poffible

-0.86

ſelves

-0.86

POSITIVE LOGITS

Py

0.94

py

0.92

Py

0.87

py

0.79

0.67

0.65

com

0.64

urg

0.63

PY

0.63

io

0.61

Activations Density 0.166%

references to the programming language Python and its various attributes or usages

No Comments

No Known Activations