INDEX

Explanations

phrases indicating success or achievement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vernote

-0.61

zmir

-0.58

fz

-0.56

 Bogen

-0.56

 Marl

-0.55

reactstrap

-0.53

Zo

-0.52

<>("

-0.52

zo

-0.52

ipan

-0.52

POSITIVE LOGITS

 SUCCESS

1.46

SUCCESS

1.42

 Success

1.41

Success

1.37

 success

1.31

 successes

1.25

isSuccessful

1.25

uccess

1.24

success

1.17

 成功

1.17

Activations Density 0.057%

phrases indicating success or achievement

No Comments

No Known Activations