INDEX

Explanations

symbols or indicate formatting within code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

↵↵

-0.67

<eos>

-0.67

↵↵↵

-0.57

↵

-0.57

><!--

-0.56

MathML

-0.52

////////////////

-0.49

を抱

-0.48

抱

-0.47

pas

-0.47

POSITIVE LOGITS

 vectorielles

0.88

Sucesor

0.87

AccessorTable

0.82

 Anſ

0.82

 tfsi

0.81

 MaterialApp

0.81

ագրություններ

0.80

 Portail

0.79

 محفوظة

0.78

 faſt

0.78

Activations Density 0.279%

symbols or indicate formatting within code snippets

No Comments

No Known Activations