INDEX

Explanations

references to businesses or firms

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

 Kela

-0.71

tabular

-0.66

이션

-0.65

HUN

-0.64

urio

-0.62

eken

-0.61

ysacchar

-0.61

 Avalon

-0.61

 Caron

-0.61

picable

-0.61

POSITIVE LOGITS

 firm

3.41

 Firm

3.26

Firm

3.22

firm

3.19

 FIRM

2.92

 Firms

2.89

 firms

2.85

 firme

2.21

Fir

2.13

 firmer

2.04

Activations Density 0.067%

references to businesses or firms

No Comments

No Known Activations

references to businesses or firms

No Comments

No Known Activations