INDEX

Explanations

references to programming concepts related to parsers

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

 Akin

-0.85

OrWhiteSpace

-0.79

jø

-0.77

 WaitForSeconds

-0.75

]=>

-0.74

writeFieldEnd

-0.73

voyez

-0.73

Tale

-0.73

ूरत

-0.72

onPressed

-0.72

POSITIVE LOGITS

parser

1.86

 parser

1.60

Parser

1.42

PARSER

1.33

 Parser

1.25

 PARSER

1.16

ArgumentParser

1.06

 argparse

0.94

parsers

0.86

 Carla

0.83

Activations Density 0.049%

references to programming concepts related to parsers

No Comments

No Known Activations