INDEX

Explanations

references to mathematical notations or formulas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

rungsseite

-0.74

PerPage

-0.70

icitis

-0.68

 motivadoras

-0.68

bewerken

-0.68

 виправивши

-0.65

 eventdata

-0.65

 RIPRODUZIONE

-0.64

 nuages

-0.63

itively

-0.63

POSITIVE LOGITS

 over

0.66

ex

0.60

 resting

0.58

 sitting

0.56

 sobre

0.55

exp

0.50

Password

0.49

interopRequire

0.48

 marks

0.46

kwds

0.46

Activations Density 0.235%

references to mathematical notations or formulas

No Comments

No Known Activations