INDEX

Explanations

adjectives describing quality or performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

TableBody

-0.53

WebMethod

-0.53

DockStyle

-0.53

($__

-0.52

SequentialGroup

-0.50

DECLARATION

-0.49

artifactId

-0.49

ORCID

-0.49

seamnă

-0.49

tomos

-0.48

POSITIVE LOGITS

 quality

0.95

 snippetHide

0.92

quality

0.86

 kwaliteit

0.74

колеп

0.73

 qualité

0.69

 QUALITY

0.68

 performance

0.68

잘

0.67

 slecht

0.66

Activations Density 0.224%

adjectives describing quality or performance

No Comments

No Known Activations