INDEX

Explanations

the presence of the word "pl" in various forms

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

PhysRev

-0.70

 Hül

-0.62

umns

-0.60

 SEDS

-0.59

 Segel

-0.56

jiny

-0.55

벳

-0.55

يكب

-0.54

ItemBackground

-0.53

Referências

-0.53

POSITIVE LOGITS

Pl

2.87

pl

2.81

pl

2.79

Pl

2.79

PL

2.75

pla

2.73

PL

2.68

Pla

2.65

pla

2.49

Pla

2.37

Activations Density 0.096%

the presence of the word "pl" in various forms

No Comments

No Known Activations