INDEX

Explanations

punctuation and numerical patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

DockStyle

-0.59

 total

-0.46

TagHelpers

-0.46

<strong>

-0.44

FRE

-0.42

 WARRANTIES

-0.41

//

-0.41

 After

-0.40

POSITIVE LOGITS

 pleaſure

1.03

 purpoſe

1.01

 myſelf

1.00

 itſelf

0.91

 Jefus

0.89

 Theſe

0.89

 houſe

0.87

 Diſ

0.87

 Monfieur

0.85

 uſe

0.84

Activations Density 0.467%

punctuation and numerical patterns

No Comments

No Known Activations