INDEX

Explanations

phrases indicating motivations and reasons behind decisions or actions

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

 AssemblyCulture

-0.88

SourceChecksum

-0.86

ContentAsync

-0.85

Efq

-0.79

évaluateur

-0.77

IUrlHelper

-0.72

 Monfieur

-0.72

 disambiguazione

-0.72

XmlAccessorType

-0.71

 Diſ

-0.68

POSITIVE LOGITS

 want

0.61

 reasons

0.57

reasons

0.56

是因为

0.56

 wanting

0.54

 REASONS

0.54

是想

0.52

REASONS

0.50

Reasons

0.49

理由は

0.49

Activations Density 0.522%

phrases indicating motivations and reasons behind decisions or actions

No Comments

No Known Activations