INDEX

Explanations

references to specific places and various types of entities or objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

Становништво

-0.52

squareup

-0.51

ContentAlignment

-0.51

 Référence

-0.50

válasz

-0.50

 Pristupljeno

-0.49

InSection

-0.49

 coefficients

-0.48

 determinations

-0.48

Garonne

-0.48

POSITIVE LOGITS

 poveznice

0.60

المناصب

0.60

Autoritní

0.58

 Italijanski

0.57

kaner

0.56

')['

0.56

 سكانية

0.54

 regional

0.53

 southern

0.53

sianic

0.52

Activations Density 0.417%

references to specific places and various types of entities or objects

No Comments

No Known Activations