INDEX

Explanations

numerical data, particularly relating to prime factors or mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Portail

-0.81

colorbar

-0.75

__).

-0.72

gäng

-0.72

jev

-0.71

orship

-0.70

ADATA

-0.70

 Gabi

-0.70

 knowled

-0.69

てる

-0.68

POSITIVE LOGITS

1.02

 CGSize

0.71

dır

0.71

 Ocho

0.69

httphttps

0.67

 consultato

0.67

0.63

 Renaud

0.62

azgo

0.62

 للاسماء

0.61

Activations Density 0.740%

numerical data, particularly relating to prime factors or mathematical expressions

No Comments

No Known Activations