INDEX

Explanations

mentions of characters and specific names within a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 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

featureID

-1.02

 nakalista

-0.96

Datuak

-0.90

RegressionTest

-0.88

Personensuche

-0.87

 Italijanski

-0.86

AndEndTag

-0.86

windowFixed

-0.85

 Biôgrafia

-0.82

RenderAtEndOf

-0.82

POSITIVE LOGITS

for

0.38

0.35

 base

0.34

as

0.34

on

0.34

 pure

0.33

do

0.33

con

0.31

one

0.30

 referred

0.30

Activations Density 0.878%

mentions of characters and specific names within a narrative context

No Comments

No Known Activations