INDEX

Explanations

directory and file-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-1.33

 pleaſure

-1.23

 Shakspeare

-1.23

 Мексичка

-1.21

 Jefus

-1.19

__":

-1.18

 Monfieur

-1.17

 Theſe

-1.17

 estekak

-1.17

 Anſ

-1.16

POSITIVE LOGITS

Bru

0.94

bru

0.74

bru

0.73

0.69

Bru

0.69

 into

0.67

dir

0.67

0.66

Activations Density 0.192%

directory and file-related terms

No Comments

No Known Activations