INDEX

Explanations

numerical values and references to formatting or coding structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dicionado

-0.84

tagHelperRunner

-0.81

 intptr

-0.80

 ErrInvalid

-0.77

ToListAsync

-0.74

SaveChangesAsync

-0.71

GraphicsUnit

-0.70

BASEPATH

-0.69

ModelSerializer

-0.69

 صوتيه

-0.68

POSITIVE LOGITS

…

0.72

….

0.64

<b>

0.63

…

0.62

ObjectModel

0.58

 ….

0.58

</i>

0.56

…..

0.55

**

0.54

<eos>

0.52

Activations Density 2.034%

numerical values and references to formatting or coding structures

No Comments

No Known Activations