INDEX

Explanations

references to subcomponents or substructures in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 }}"></

-0.96

parseColor

-0.88

?>>

-0.88

 ?>">

-0.85

 kaynağından

-0.84

="#">

-0.83

 Floren

-0.83

 ModelExpression

-0.82

colorPrimary

-0.82

 BorderRadius

-0.81

POSITIVE LOGITS

sub

1.91

SUB

1.80

Sub

1.77

SUB

1.76

sub

1.58

Sub

1.57

 subs

1.52

 getSub

1.38

getSub

1.32

サブ

1.26

Activations Density 0.145%

references to subcomponents or substructures in a technical context

No Comments

No Known Activations