INDEX

Explanations

references to graphical representations of data or processes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 متعلقه

-0.90

躇

-0.74

Datuak

-0.74

IContainer

-0.69

encanaan

-0.66

 ());

-0.65

antaranya

-0.64

 masculinos

-0.63

Alike

-0.61

***************

-0.60

POSITIVE LOGITS

 curve

2.03

 curves

2.02

curve

1.91

 Curves

1.90

 Curve

1.84

curves

1.78

Curve

1.67

Curves

1.55

 curvas

1.29

 curva

1.21

Activations Density 0.088%

references to graphical representations of data or processes

No Comments

No Known Activations