INDEX

Explanations

references to legal proceedings and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 organisational

-0.89

 mobilisation

-0.86

organised

-0.85

 Organisations

-0.85

 realisation

-0.83

 organised

-0.83

 honourable

-0.81

 civilisation

-0.81

 authorisation

-0.80

 utilisation

-0.79

POSITIVE LOGITS

richTextPanel

0.63

 hâte

0.61

ighbor

0.60

toward

0.59

 flavor

0.59

 colored

0.59

 traveler

0.58

uș

0.57

 travelers

0.57

 Toward

0.56

Activations Density 0.053%

references to legal proceedings and related terms

No Comments

No Known Activations