INDEX

Explanations

references to specific data structures or programming elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

regler

-0.60

Apu

-0.56

rends

-0.52

توض

-0.52

เงิน

-0.51

!("{}",

-0.50

Ổ

-0.50

ΕΙ

-0.50

 crippled

-0.49

 orquí

-0.49

POSITIVE LOGITS

Add

1.61

Add

1.53

add

1.27

add

1.26

ADD

1.16

ADD

1.05

 Adding

0.94

AddWithValue

0.93

 adding

0.92

Adding

0.92

Activations Density 0.012%

references to specific data structures or programming elements

No Comments

No Known Activations