INDEX

Explanations

references to hierarchical government positions and departments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

literals

-0.40

thâu

-0.38

outi

-0.37

Essex

-0.36

Démographie

-0.35

Actions

-0.35

FieldDescriptor

-0.34

bių

-0.34

ToAction

-0.34

Action

-0.34

POSITIVE LOGITS

 bezeichneter

0.52

ValueStyle

0.50

Efq

0.45

 awakeFromNib

0.45

InSection

0.44

原始内容存档于

0.44

 المعيارى

0.43

ResumeLayout

0.42

 OMITBAD

0.42

#+#

0.42

Activations Density 0.308%

references to hierarchical government positions and departments

No Comments

No Known Activations