INDEX

Explanations

references to individuals, particularly those prefixed with titles like "Mr." or "Dr."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

basicConfig

-0.76

wahati

-0.76

']")

-0.71

=()

-0.70

]**

-0.69

])).

-0.66

]^{\

-0.65

COD

-0.65

."</

-0.64

*-*-

-0.64

POSITIVE LOGITS

Mr

1.26

Mr

1.20

mr

1.02

 Mister

1.02

Mrs

0.96

Mrs

0.93

MR

0.91

Mister

0.88

 Sirs

0.87

قای

0.87

Activations Density 0.073%

references to individuals, particularly those prefixed with titles like "Mr." or "Dr."

No Comments

No Known Activations