INDEX

Explanations

technical specifications and measurements related to experimental methods

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

 насељу

-0.73

AutoScaleMode

-0.72

Personensuche

-0.65

trä

-0.62

ὺ

-0.60

anskrit

-0.57

 MonoBehaviour

-0.55

 diagonal

-0.54

 Yoshida

-0.54

enheim

-0.54

POSITIVE LOGITS

<tr>

0.71

0.68

↵↵

0.67

]")]

0.64

</h6>

0.63

ništvo

0.62

<eos>

0.60

DoubleQuotes

0.60

</h4>

0.57

,))

0.57

Activations Density 0.163%

technical specifications and measurements related to experimental methods

No Comments

No Known Activations