INDEX

Explanations

phrases that summarize key findings or conclusions in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 extra

-0.44

 springfox

-0.42

 ulter

-0.41

пса

-0.41

 Extra

-0.41

Ver

-0.40

me

-0.40

 Super

-0.39

edd

-0.39

زا

-0.38

POSITIVE LOGITS

 Majefty

0.91

Efq

0.88

 Theſe

0.84

 houſe

0.83

 Normdatei

0.83

 Houſe

0.83

TagMode

0.79

 ſind

0.78

 Jefus

0.77

 Diſ

0.76

Activations Density 0.364%

phrases that summarize key findings or conclusions in a document

No Comments

No Known Activations