INDEX

Explanations

references to authors or cited works in academic writing

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

 Reſ

-0.75

 fubject

-0.73

 houſe

-0.73

 Houſe

-0.73

 pleaſure

-0.72

 ſche

-0.71

 Anſ

-0.71

 Monfieur

-0.71

 Jefus

-0.71

 purpoſe

-0.71

POSITIVE LOGITS

出版年

0.62

 Мексичка

0.52

addPreferredGap

0.50

Pautan

0.50

NSIndexPath

0.50

LoadScene

0.50

Le

0.49

PutMapping

0.49

dracht

0.49

 أعلام

0.49

Activations Density 0.218%

references to authors or cited works in academic writing

No Comments

No Known Activations