INDEX

Explanations

items related to data structures, specifically indications of structure and organization in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Monfieur

-0.89

 Theſe

-0.84

|}{$

-0.83

 Verſ

-0.78

 Lizzy

-0.77

 depositphotos

-0.74

 Diſ

-0.74

 Majefty

-0.74

 Anſ

-0.72

 ―――――

-0.72

POSITIVE LOGITS

</em>

0.94

</strong>

0.81

</h2>

0.77

↵

0.73

</h3>

0.72

</

0.72

</sub>

0.69

</

0.67

</code>

0.66

Activations Density 0.022%

items related to data structures, specifically indications of structure and organization in programming contexts

No Comments

No Known Activations