INDEX

Explanations

occurrences of significant events or 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

Hentet

-0.81

 nahilalakip

-0.80

extAlignment

-0.77

 EconPapers

-0.76

httphttps

-0.74

writeFieldEnd

-0.71

 <>",

-0.71

MessageTagHelper

-0.71

awtextra

-0.70

 CanadaChoose

-0.69

POSITIVE LOGITS

 then

0.44

しまいました

0.34

 eventually

0.32

then

0.32

Dr

0.31

 przep

0.28

เอ

0.28

ทัน

0.27

感

0.27

 further

0.26

Activations Density 0.582%

occurrences of significant events or actions

No Comments

No Known Activations