INDEX

Explanations

technical terminology related to programming concepts and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.52

EndProject

-0.51

ArgsConstructor

-0.49

-0.47

…

-0.46

 tech

-0.46

-0.45

lett

-0.45

Pyx

-0.44

py

-0.44

POSITIVE LOGITS

 iſt

0.96

 purpoſe

0.95

Eſ

0.93

 pleaſure

0.92

 auffi

0.91

NUMX

0.90

 Diſ

0.88

ſelves

0.88

ſelf

0.87

 Monfieur

0.86

Activations Density 1.252%

technical terminology related to programming concepts and syntax

No Comments

No Known Activations