INDEX

Explanations

empty object structures in code or data definitions

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

<td>

-0.63

-0.59

 train

-0.47

">

-0.47

 Prest

-0.46

)):

-0.46

ải

-0.45

 Train

-0.45

POSITIVE LOGITS

{}

0.92

{};

0.91

={};

0.85

({});

0.83

{}

0.81

={}

0.79

{};

0.73

{},

0.71

({})

0.71

("{}

0.69

Activations Density 0.052%

empty object structures in code or data definitions

No Comments

No Known Activations