INDEX

Explanations

phrases indicating uncertainty or doubt

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Sardin

-0.83

 Sardinia

-0.83

Efq

-0.81

 JSTOR

-0.79

 Majefty

-0.75

 Athenians

-0.74

hla

-0.73

OGND

-0.72

 Florentine

-0.70

 Benth

-0.69

POSITIVE LOGITS

 Réponses

0.76

atche

0.64

 CanadaChoose

0.64

ranton

0.63

unmodifiable

0.60

 zamanda

0.59

 estekak

0.59

 NSCoder

0.58

writeFieldEnd

0.58

StructEnd

0.57

Activations Density 0.219%

phrases indicating uncertainty or doubt

No Comments

No Known Activations