INDEX

Explanations

phrases that reference the details or specifics of a subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ագրություններ

-0.86

 otomatig

-0.81

 Cowper

-0.81

 Wilber

-0.74

 Cups

-0.71

 Covent

-0.71

GridColumn

-0.71

 CUCET

-0.70

zzang

-0.70

ôles

-0.70

POSITIVE LOGITS

 details

3.00

 Details

2.62

details

2.51

Details

2.48

 DETAILS

2.30

 detail

2.14

DETAILS

2.08

 detalles

1.98

 détails

1.98

 detalhes

1.93

Activations Density 0.069%

phrases that reference the details or specifics of a subject

No Comments

No Known Activations