INDEX

Explanations

specific individuals and references in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

<i>

-0.60

<sub>

-0.52

<em>

-0.49

Marianne

-0.46

Patron

-0.45

<b>

-0.45

Dropbox

-0.45

↵

-0.44

<sup>

-0.43

Dich

-0.43

POSITIVE LOGITS

 habet

0.63

NewUrlParser

0.62

 juſ

0.61

ագրություններ

0.59

 gesteld

0.59

initComponents

0.58

SpringBootTest

0.58

 raiſ

0.57

 neceſſ

0.55

 pleaſure

0.54

Activations Density 2.743%

specific individuals and references in various contexts

No Comments

No Known Activations