INDEX

Explanations

references to data models in programming or API contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Efq

-1.19

 pleaſure

-0.99

 themſelves

-0.99

 تضيفلها

-0.97

 Monfieur

-0.95

 Jefus

-0.95

 myſelf

-0.95

 Shakspeare

-0.94

 himſelf

-0.91

 Theſe

-0.90

POSITIVE LOGITS

Model

1.53

 Model

1.52

model

1.49

 model

1.25

 MODEL

1.21

MODEL

1.15

setModel

1.00

Models

0.94

getModel

0.88

ItemModel

0.88

Activations Density 0.040%

references to data models in programming or API contexts

No Comments

No Known Activations