INDEX

Explanations

programming-related keywords and functions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personendaten

-0.97

EDEFAULT

-0.94

 صوتيه

-0.93

awtextra

-0.87

 дописавши

-0.82

CloseOperation

-0.82

antMatchers

-0.81

IntoConstraints

-0.79

AndEndTag

-0.78

اریخ

-0.78

POSITIVE LOGITS

 Cæsar

0.89

 purpoſe

0.84

 myſelf

0.83

 greateſt

0.81

 Chriftian

0.76

 houſe

0.76

 themſelves

0.75

 reaſon

0.75

 ſeveral

0.73

 Diſ

0.73

Activations Density 0.768%

programming-related keywords and functions

No Comments

No Known Activations