INDEX

Explanations

references to the current object in code

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

enterOuterAlt

-0.62

 uska

-0.60

AddTagHelper

-0.58

estand

-0.55

oten

-0.53

+(\

-0.53

fertig

-0.51

 annen

-0.51

EndProject

-0.51

이터

-0.51

POSITIVE LOGITS

selves

0.86

 oneself

0.85

 herself

0.84

 selves

0.84

self

0.83

 MonoBehaviour

0.80

 thyself

0.78

 yourself

0.75

 Himself

0.75

 himself

0.73

Activations Density 0.029%

references to the current object in code

No Comments

No Known Activations