INDEX

Explanations

specific nouns and terms related to scientific and technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

Personendaten

-0.92

 resourceCulture

-0.85

 CreateTagHelper

-0.85

DockStyle

-0.78

 ویکی‌پدی

-0.71

 EconPapers

-0.70

AddTagHelper

-0.69

tagHelperRunner

-0.69

ftagPool

-0.64

 <>",

-0.63

POSITIVE LOGITS

alom

0.39

AMILY

0.36

FLAT

0.33

minLength

0.32

roll

0.32

urg

0.31

JTable

0.30

MINOR

0.30

ковский

0.30

찮

0.30

Activations Density 0.504%

specific nouns and terms related to scientific and technical contexts

No Comments

No Known Activations