INDEX

Explanations

references to characters and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

harusnya

-0.57

 instruk

-0.53

chy

-0.53

Chy

-0.53

servername

-0.51

 pourtant

-0.50

ToObject

-0.50

meuble

-0.49

 recal

-0.49

bidden

-0.49

POSITIVE LOGITS

+#+#

0.66

fortawesome

0.66

 propOrder

0.64

GraphicsUnit

0.58

 pinulongan

0.57

 ostavi

0.56

SequentialGroup

0.54

 GenerationType

0.53

Välislingid

0.52

 autorytatywna

0.52

Activations Density 0.364%

references to characters and their attributes

No Comments

No Known Activations