INDEX

Explanations

mentions of accounts and their related terms in a context of account management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 GenerationType

-0.95

Vle

-0.86

httphttps

-0.79

expiresIn

-0.79

 Schme

-0.78

равда

-0.77

 inappropriés

-0.74

terday

-0.72

größern

-0.72

impin

-0.70

POSITIVE LOGITS

 account

2.30

 accounts

2.25

 Account

2.16

account

2.10

 Accounts

2.07

Account

2.04

 ACCOUNT

1.98

accounts

1.98

 getAccount

1.94

Accounts

1.89

Activations Density 0.038%

mentions of accounts and their related terms in a context of account management

No Comments

No Known Activations