INDEX

Explanations

terms related to encouragement and support for action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

id

-0.77

as

-0.71

ber

-0.69

lands

-0.68

}{|

-0.67

io

-0.66

fe

-0.64

bed

-0.63

-0.62

 Dios

-0.61

POSITIVE LOGITS

 encouraged

1.74

 encourages

1.71

 encourage

1.67

 Encourage

1.67

couraged

1.63

Encourage

1.60

 encouragement

1.60

 encor

1.43

 encourag

1.42

couraging

1.41

Activations Density 0.096%

terms related to encouragement and support for action

No Comments

No Known Activations