INDEX

Explanations

terms related to objectives, achievements, and the desire for specific outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

<bos>

-0.31

स्

-0.29

 collectively

-0.29

 former

-0.27

стра

-0.27

})-\

-0.27

})).

-0.27

EndContext

-0.26

 Fürst

-0.26

Gi

-0.26

POSITIVE LOGITS

 Bewußt

0.69

angliski

0.67

 zuſammen

0.67

UnusedPrivate

0.65

 zwiſchen

0.64

WebElementEntity

0.63

 queſto

0.61

@[+][

0.60

 الرياضيه

0.59

 Inscrivez

0.58

Activations Density 0.185%

terms related to objectives, achievements, and the desire for specific outcomes

No Comments

No Known Activations