INDEX

Explanations

titles and metadata associated with documents or papers

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

 vostri

-0.77

 sentire

-0.63

 puissiez

-0.63

 étoient

-0.58

 avoient

-0.57

 supplémentaires

-0.57

 RIPRODUZIONE

-0.56

 procedere

-0.55

 trekken

-0.55

 gezegd

-0.55

POSITIVE LOGITS

Title

2.01

 Title

1.76

 title

1.39

title

1.36

 TITLE

1.36

 Titles

1.10

TITLE

1.09

 titles

1.03

 Titel

1.03

Titles

0.97

Activations Density 0.042%

titles and metadata associated with documents or papers

No Comments

No Known Activations