INDEX

Explanations

references to combinations or blends of different elements or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

}{*}{

-0.58

 calorías

-0.52

lük

-0.51

 portas

-0.49

assies

-0.48

لمانيا

-0.48

defaultProps

-0.48

 almendras

-0.47

</tfoot>

-0.46

แก่

-0.45

POSITIVE LOGITS

MIX

1.19

MIX

1.07

mix

1.05

Mix

1.02

 mixes

1.01

Mix

0.96

mix

0.95

 Mixed

0.90

Mixed

0.89

 mixed

0.88

Activations Density 0.076%

references to combinations or blends of different elements or categories

No Comments

No Known Activations