INDEX

Explanations

terms and symbols related to stress, strain, and variances in scientific contexts

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

 Amiens

-0.76

 techniczne

-0.74

fdf

-0.69

ategorie

-0.69

 Houſe

-0.69

Ait

-0.68

EPR

-0.67

 Vittorio

-0.67

 Cougars

-0.65

 sats

-0.64

POSITIVE LOGITS

 sigma

1.02

σ

1.02

sigma

1.00

 Paulson

0.93

setVerticalGroup

0.91

σ

0.90

DAQ

0.87

 Woodward

0.84

 Maguire

0.83

CEAN

0.80

Activations Density 0.300%

terms and symbols related to stress, strain, and variances in scientific contexts

No Comments

No Known Activations