INDEX

Explanations

expressions indicating perception or opinion about something's significance or clarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 correctes

-0.60

RenderAtEndOf

-0.56

StreetMap

-0.56

deauna

-0.54

 paff

-0.52

 distanciation

-0.51

 CanadaChoose

-0.51

 متحد

-0.50

 Ronan

-0.49

NameInMap

-0.48

POSITIVE LOGITS

 complex

0.98

 complicated

0.90

 esoteric

0.88

complex

0.79

 arcane

0.74

 technical

0.70

complicated

0.69

 komplex

0.68

 Complex

0.68

 abstract

0.68

Activations Density 0.349%

expressions indicating perception or opinion about something's significance or clarity

No Comments

No Known Activations