INDEX

Explanations

references to adapters and adaptation-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 propOrder

-0.88

 Fillmore

-0.80

SLS

-0.76

 présidentielle

-0.74

 Shiloh

-0.70

ajuato

-0.70

seamnă

-0.70

 tiet

-0.69

 hydrochloric

-0.69

Columb

-0.68

POSITIVE LOGITS

 adapted

1.09

TableAdapter

1.06

 adapter

1.05

APTER

1.03

Adapter

1.03

 Adapter

1.01

adap

1.00

 adapting

1.00

adapted

0.96

Adap

0.96

Activations Density 0.177%

references to adapters and adaptation-related concepts

No Comments

No Known Activations