INDEX

Explanations

questions and discussions surrounding character motivations and plot events in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Duluth

-0.61

 ExecuteAsync

-0.60

 Cita

-0.58

 Khan

-0.58

fastjson

-0.58

 Buffalo

-0.58

 Citation

-0.57

Buffalo

-0.54

 Rochelle

-0.53

CDT

-0.52

POSITIVE LOGITS

 Harry

1.11

 Hogwarts

1.08

 Potter

1.04

 Hermione

1.03

 Dumbledore

1.01

Harry

1.00

 Voldemort

0.99

 Malfoy

0.98

 Snape

0.94

 Weasley

0.94

Activations Density 0.198%

questions and discussions surrounding character motivations and plot events in a narrative context

No Comments

No Known Activations