INDEX

Explanations

proper nouns related to individuals, places, and specific titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

BibitemShut

-0.92

 Савезне

-0.88

 Италијани

-0.81

"])

-0.78

'),

-0.78

]$}

-0.78

__':

-0.78

érables

-0.77

"],

-0.77

Personendaten

-0.77

POSITIVE LOGITS

del

0.58

Af

0.53

qua

0.51

 Fran

0.51

qu

0.50

imo

0.49

af

0.49

Fran

0.49

Mar

0.48

Activations Density 0.431%

proper nouns related to individuals, places, and specific titles

No Comments

No Known Activations