INDEX

Explanations

technical terms related to physical mechanisms and measurements

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

']))

-0.92

 Jacobsen

-0.85

 nahilalakip

-0.85

"])

-0.80

 Jacobson

-0.77

CodeAttribute

-0.76

ratulations

-0.75

"}

-0.74

″]

-0.74

'])

-0.73

POSITIVE LOGITS

 Lend

0.93

 Shakspeare

0.92

 pleaſure

0.89

 Monfieur

0.88

 ſtand

0.84

 Heal

0.84

 cauſe

0.83

 gild

0.82

 Garnish

0.82

 Greet

0.81

Activations Density 1.091%

technical terms related to physical mechanisms and measurements

No Comments

No Known Activations