INDEX

Explanations

references to people and their roles or affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

ceği

-0.46

 виправивши

-0.45

ख्या

-0.44

ftagPool

-0.42

Presentación

-0.39

TagMode

-0.39

 BorderRadius

-0.38

alpa

-0.37

телен

-0.37

lık

-0.37

POSITIVE LOGITS

 said

2.86

 says

2.79

said

2.43

says

2.37

 Says

2.30

Says

2.26

 mengatakan

2.25

 saying

2.25

say

2.16

Said

2.13

Activations Density 1.309%

references to people and their roles or affiliations

No Comments

No Known Activations