INDEX

Explanations

references to businesses or organizations identified as firms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

-0.77

ysacchar

-0.74

ανά

-0.71

 shearing

-0.68

 Felton

-0.67

HUN

-0.65

Jez

-0.64

 Caron

-0.63

TAL

-0.63

achio

-0.62

POSITIVE LOGITS

 firm

2.88

 Firm

2.69

Firm

2.68

firm

2.61

 firms

2.50

 Firms

2.41

 FIRM

2.31

 firme

1.89

Fir

1.82

 firmer

1.74

Activations Density 0.076%

references to businesses or organizations identified as firms

No Comments

No Known Activations