INDEX

Explanations

structured data and object literals 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 @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

protoimpl

-0.71

“

-0.64

 ExecuteAsync

-0.63

رشف

-0.62

 BorderRadius

-0.61

hdashline

-0.60

IDATE

-0.58

Rhestr

-0.58

ScopeManager

-0.58

 linkovi

-0.57

POSITIVE LOGITS

={

3.29

={

1.85

={

1.76

]={

1.62

={(

1.48

={[

1.46

={{

1.36

={()

1.34

={}

1.28

={},

1.19

Activations Density 0.109%

structured data and object literals in code

No Comments

No Known Activations