INDEX

Explanations

proper nouns and names, particularly those related to people and places

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

 Weber

-0.82

ftagPool

-0.78

المناصب

-0.77

Weber

-0.70

EMPL

-0.68

romycin

-0.68

 Hale

-0.67

Ligações

-0.66

Hale

-0.65

 Schein

-0.64

POSITIVE LOGITS

 crocodiles

0.82

 Gladstone

0.74

 Clem

0.73

 flushed

0.73

 cheeks

0.73

 Sist

0.70

 Clovis

0.70

 crocodile

0.70

Cle

0.69

 oocytes

0.68

Activations Density 1.058%

proper nouns and names, particularly those related to people and places

No Comments

No Known Activations