INDEX

Explanations

sections and headers of lists or structured content in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ագրություններ

-0.69

 surla

-0.69

iſten

-0.60

iſen

-0.60

tagHelperRunner

-0.59

ſcher

-0.59

出版年

-0.59

 kasarigan

-0.57

principalColumn

-0.57

Portail

-0.56

POSITIVE LOGITS

BufferException

0.42

 dran

0.37

...

0.35



0.35

 last

0.35

 proof

0.35

…

0.34

Parcelable

0.34

0.32

Activations Density 0.007%

sections and headers of lists or structured content in documents

No Comments

No Known Activations