INDEX

Explanations

instances of the word "rank" and its variations in the context of ranking or rating

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

cjs

-0.64

 ―――――

-0.61

谑

-0.60

 rhestr

-0.60

gether

-0.60

 BoxFit

-0.60

ThemeOverlay

-0.59

/*---

-0.58

$_"

-0.58

 Gains

-0.58

POSITIVE LOGITS

[:,

1.48

(:,

1.20

[:,:,

0.81

(:,:,

0.78

**

0.69

classmethod

0.69

 rank

0.67

[...,

0.67

**

0.65

rank

0.62

Activations Density 0.210%

instances of the word "rank" and its variations in the context of ranking or rating

No Comments

No Known Activations