INDEX

Explanations

associations and relationships between different sensory features

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

]<<"

-0.56

]<=

-0.55

IVEREF

-0.53

 EdgeInsets

-0.48

'");

-0.45

()]

-0.42

GIVEREF

-0.42

'></

-0.42

fromLTRB

-0.42

คาร

-0.41

POSITIVE LOGITS

UnsafeEnabled

0.68

 Baillargeon

0.62

ITI

0.59

AnimationsModule

0.59

numerusform

0.58

éroport

0.57

InSection

0.55

 AssemblyCulture

0.55

 jsPsych

0.54

ULUS

0.54

Activations Density 2.161%

associations and relationships between different sensory features

No Comments

No Known Activations

associations and relationships between different sensory features

No Comments

No Known Activations