INDEX

Explanations

terms related to electrical components or systems

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

er

-1.09

 Madsen

-0.85

GMENT

-0.73

 Hamlin

-0.72

<strong>

-0.71

 fortuna

-0.71

 góry

-0.71

 rois

-0.70

 Guthrie

-0.70

Portale

-0.69

POSITIVE LOGITS

 Clarissa

0.88

EMB

0.87

 Alyssa

0.86

 Krav

0.85

Prag

0.84

 McKinnon

0.82

 Hert

0.80

 Huntingdon

0.80

 Hebron

0.79

 Etrus

0.79

Activations Density 0.127%

terms related to electrical components or systems

No Comments

No Known Activations