INDEX

Explanations

references to characters with hierarchical titles and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 ModelExpression

-0.98

 themſelves

-0.92

+#+

-0.89

 purpoſe

-0.85

 himſelf

-0.83

 ſmall

-0.83

 विश्वसनीयता

-0.82

-0.81

 متعلقه

-0.81

RenderAtEndOf

-0.78

POSITIVE LOGITS

0.64

0.63

boy

0.47

les

0.45

Boy

0.45

Mar

0.44

Sir

0.43

fre

0.42

...

0.42

boy

0.41

Activations Density 0.060%

references to characters with hierarchical titles and relationships

No Comments

No Known Activations