INDEX

Explanations

terms related to excessive or inflated estimates and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Datuak

-0.75

Спољашње

-0.57

 paesaggio

-0.54

 uninterrupted

-0.54

 /\.(

-0.53

 snippetHide

-0.53

SourceChecksum

-0.52

yelidikan

-0.51

EFIAPI

-0.51

Números

-0.51

POSITIVE LOGITS

Too

0.77

 overkill

0.76

Too

0.75

 exces

0.74

 overs

0.71

 excessive

0.71

too

0.70

 overuse

0.70

 Overs

0.69

 overly

0.68

Activations Density 0.416%

terms related to excessive or inflated estimates and their implications

No Comments

No Known Activations