INDEX

Explanations

terms related to architecture and architectural design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 يتيمه

-0.97

 Ding

-0.73

DataMember

-0.69

DMT

-0.69

ImageField

-0.67

ers

-0.65

irical

-0.63

 vnder

-0.63

CommandText

-0.63

Sanders

-0.61

POSITIVE LOGITS

PerformLayout

1.16

 Archibald

1.09

"]();

0.93

 Hero

0.92

tôi

0.90

]--;

0.89

houette

0.88

])):

0.86

InputTagHelper

0.85

ipelago

0.85

Activations Density 0.248%

terms related to architecture and architectural design

No Comments

No Known Activations