INDEX

Explanations

phrases discussing lessons learned and insights gained from experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

secuted

-0.50

andExpect

-0.48

 consultato

-0.46

dań

-0.45

ELINE

-0.44

ughter

-0.43

asantry

-0.43

త్ర

-0.43

ularia

-0.43

rasco

-0.42

POSITIVE LOGITS

 learn

3.36

 learning

3.17

 learned

3.10

 learns

3.10

learn

2.94

 Learn

2.79

 learnt

2.77

 LEARN

2.75

Learn

2.71

learning

2.71

Activations Density 0.452%

phrases discussing lessons learned and insights gained from experiences

No Comments

No Known Activations