INDEX

Explanations

structured data elements or references within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

InputTagHelper

-0.63

 NSCoder

-0.53



-0.47

 AssemblyCulture

-0.37

öße

-0.36

outState

-0.36

 kepem

-0.35

 kiệm

-0.35

GeneratedValue

-0.35

❃

-0.34

POSITIVE LOGITS

 يتيمه

0.65

tagHelperRunner

0.56

principalTable

0.56

verifyException

0.56

interopRequire

0.56

érature

0.55

OCCURRED

0.53

ArrowToggle

0.52

Élet

0.52

 initComponents

0.51

Activations Density 7.574%

structured data elements or references within a document

No Comments

No Known Activations