INDEX

Explanations

terms that denote relationships among peer groups or social categories

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

orghini

-0.42

uminescence

-0.42

 '\\;'

-0.42

 Forestry

-0.41

 المعيارى

-0.41

ndham

-0.41

 Rockefeller

-0.39

 GenerationType

-0.39

!(:

-0.39

forestation

-0.39

POSITIVE LOGITS

 counterpart

0.84

 colleague

0.82

 neighbor

0.82

 peer

0.81

 Peer

0.79

Neighbor

0.79

 peers

0.79

 partner

0.79

 teammate

0.79

Peer

0.78

Activations Density 0.292%

terms that denote relationships among peer groups or social categories

No Comments

No Known Activations