INDEX

Explanations

terms and phrases related to diagnostics

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

AccessorTable

-1.13

complexContent

-1.04

parsedMessage

-1.00

 autorytatywna

-0.97

AsUp

-0.97

 snippetHide

-0.96

InjectAttribute

-0.94

enterOuterAlt

-0.92

########.

-0.91

:✨

-0.90

POSITIVE LOGITS

Diagnostics

2.31

 diagnostics

1.30

 Diagnostics

1.24

 diagnostic

1.15

diagnostics

1.06

 Diagnostic

1.06

 DIAG

0.97

Diagnostic

0.97

diagnostic

0.94

 diagnos

0.89

Activations Density 0.043%

terms and phrases related to diagnostics

No Comments

No Known Activations