INDEX

Explanations

references to notable historical events and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 plankton

-0.49

 Zwick

-0.48

 produttore

-0.48

NOPQRST

-0.48

 Innen

-0.46

מר

-0.46

 personnelles

-0.45

 généraux

-0.45

panning

-0.44

zez

-0.44

POSITIVE LOGITS

abancı

0.62

 AssemblyTitle

0.62

+#+

0.62

ContentAsync

0.60

WithIOException

0.59

 FetchType

0.59

Brought

0.58

 varargin

0.58

DotNetBar

0.58

 EconPapers

0.58

Activations Density 0.388%

references to notable historical events and entities

No Comments

No Known Activations