INDEX

Explanations

occurrences of parsing-related functions and terms in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endregion

-0.58

Personendaten

-0.57

WaitGroup

-0.55

LookAnd

-0.53

 glyphicon

-0.52

posedge

-0.50

 PeEnEo

-0.49

 חיצוניים

-0.49

Personensuche

-0.48

Manbalar

-0.48

POSITIVE LOGITS

parse

1.54

 parse

1.48

 Parse

1.45

Parse

1.41

 parsing

1.30

parser

1.27

 parser

1.27

Parser

1.24

 Parser

1.17

 Parsing

1.17

Activations Density 0.146%

occurrences of parsing-related functions and terms in code

No Comments

No Known Activations