INDEX

Explanations

documentation and return statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

UserScript

-0.57

uxxxx

-0.54

AddTagHelper

-0.53

 CanadaChoose

-0.52

tangentMode

-0.52

ThroughAttribute

-0.51

 oprot

-0.50

 GenerationType

-0.50

expandindo

-0.50

ArrowToggle

-0.50

POSITIVE LOGITS

 propOrder

0.46

 amitié

0.43

 vaisselle

0.43

 zijne

0.41

 bonté

0.41

 kysy

0.39

 bénéficiaire

0.38

Personendaten

0.38

 desnuda

0.38

 mijne

0.38

Activations Density 0.004%

documentation and return statements in code

No Comments

No Known Activations