INDEX

Explanations

HTML header tags

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ing

-1.36

ة

-0.94

ς

-0.89

ING

-0.82

 Gentry

-0.79

 gentry

-0.77

ní

-0.77

CardType

-0.77

fficients

-0.76

lys

-0.72

POSITIVE LOGITS

<h1>

1.47

../../

0.90

/>";

0.80

$",

0.79

ufac

0.77

 Cowan

0.76

UpInside

0.75

Zeneca

0.74

 ControllerBase

0.73

iastical

0.72

Activations Density 0.219%

HTML header tags

No Comments

No Known Activations