INDEX

Explanations

function or method declarations in code

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 banget

-0.55

 Shang

-0.54

 features

-0.54

 Faraday

-0.54

 hood

-0.54

д

-0.52

ad

-0.51

athione

-0.51

Shang

-0.51

CJK

-0.50

POSITIVE LOGITS

*)

1.93

*)

1.39

*)(

1.27

**)

1.18

*>(

1.18

*>(

1.12

*)&

1.12

*)(

1.12

extAlignment

0.90

*)&

0.90

Activations Density 0.084%

function or method declarations in code

No Comments

No Known Activations