INDEX

Explanations

discussions of accessibility and limitations within methodologies or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 préfé

-0.49

ggi

-0.45

 sete

-0.44

 popolari

-0.43

 instead

-0.42

代わりに

-0.41

waża

-0.39

út

-0.39

с

-0.39

tur

-0.38

POSITIVE LOGITS

ViewFeatures

0.83

 CreateTagHelper

0.78

MergeFrom

0.75

ModelAdmin

0.73

IUrlHelper

0.72

 виправивши

0.72

CodedInputStream

0.71

reportWebVitals

0.69

Brainz

0.69

 defStyleAttr

0.69

Activations Density 0.245%

discussions of accessibility and limitations within methodologies or systems

No Comments

No Known Activations