INDEX

Explanations

references to including or excluding content or information

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

 GenerationType

-1.00

 ***/

-0.91

 BorderRadius

-0.88

 }}"></

-0.87

 jScrollPane

-0.82

 LoggerFactory

-0.75

/***

-0.74

posedge

-0.73

Bakgrunnsstoff

-0.69

 initComponents

-0.69

POSITIVE LOGITS

 include

1.53

 includes

1.50

 included

1.49

 Include

1.48

 INCLUDE

1.48

Includes

1.47

 Includes

1.39

Include

1.35

includes

1.35

 Included

1.35

Activations Density 0.105%

references to including or excluding content or information

No Comments

No Known Activations