INDEX

Explanations

specific entities or items related to media, such as publishers or television series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

RegressionTest

-0.76

+#+

-0.70

 nahilalakip

-0.70

+#+#

-0.66

Chham

-0.65

inSlope

-0.64

InSection

-0.63

styleType

-0.62

 مشين

-0.62

 invokingState

-0.60

POSITIVE LOGITS

󠁿

0.68

 arşivlendi

0.47

].

0.46

#:

0.45

AnchorTagHelper

0.45

BindingResult

0.45

 medios

0.44

rillation

0.44

RequestQueue

0.44

((

0.43

Activations Density 0.192%

specific entities or items related to media, such as publishers or television series

No Comments

No Known Activations