INDEX

Explanations

references to online data and user interactions

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

 AssemblyTitle

-1.07

ArgsConstructor

-0.96

niająca

-0.95

addCriterion

-0.90

endphp

-0.90

IBOutlet

-0.85

 beginnetje

-0.85

rungsseite

-0.80

 estimés

-0.79

 InputDecoration

-0.79

POSITIVE LOGITS

mstyle

0.47

erdings

0.42

υσ

0.42

 plus

0.41

 Midway

0.41

Afterwards

0.41

 Afterwards

0.41

 jadx

0.40

 afterwards

0.40

 themselves

0.40

Activations Density 0.036%

references to online data and user interactions

No Comments

No Known Activations