INDEX

Explanations

references to requests, responsibilities, and the consequences of actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 lèvres

-0.32

 başına

-0.31

its

-0.31

 extérieures

-0.31

 kendini

-0.30

 والذي

-0.30

 itself

-0.29

 oreilles

-0.28

 samego

-0.28

Neues

-0.28

POSITIVE LOGITS

 themselves

1.25

themselves

1.20

Their

1.09

their

1.02

 Their

0.98

 their

0.97

they

0.96

 Mereka

0.94

 They

0.93

They

0.91

Activations Density 0.386%

references to requests, responsibilities, and the consequences of actions

No Comments

No Known Activations