INDEX

Explanations

references to the reliability and validity of tests, scales, and questionnaires

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

省市镇

-0.49

 Unwin

-0.49

 actionMode

-0.49

ConstraintMaker

-0.49

SpringRunner

-0.48

 uintptr

-0.47

 Gennaio

-0.47

 ganglion

-0.46

devtool

-0.45

 ricor

-0.45

POSITIVE LOGITS

 scale

1.01

 scales

0.96

 Scale

0.95

 scoring

0.93

 item

0.93

 items

0.93

 instrument

0.92

 scores

0.87

scoring

0.84

scales

0.83

Activations Density 0.820%

references to the reliability and validity of tests, scales, and questionnaires

No Comments

No Known Activations