INDEX

Explanations

occurrences of the word "tf" and its variations, indicating a focus on certain programming or technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ъ

-0.61

 Lawler

-0.59

 Aéroport

-0.56

 sitesinde

-0.55

Nek

-0.54

areth

-0.52

 Lazarus

-0.52

 sumpay

-0.51

◄

-0.51

acea

-0.51

POSITIVE LOGITS

nome

0.86

Wi

0.84

 wireType

0.83

Nombre

0.78

PerformLayout

0.74

Whilst

0.73

 المعيارى

0.72

wi

0.72

nombre

0.72

 nahilalakip

0.71

Activations Density 0.122%

occurrences of the word "tf" and its variations, indicating a focus on certain programming or technical terms

No Comments

No Known Activations