INDEX

Explanations

references to individuals identified as "Mr." followed by a name or title

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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



-0.85

COD

-0.82

wahati

-0.79

ICD

-0.77

Pozdrawiam

-0.77

=()

-0.76

']")

-0.76

 Strafe

-0.76

basicConfig

-0.75

 defaultstate

-0.74

POSITIVE LOGITS

Mr

1.69

Mr

1.68

mr

1.31

mr

1.17

Mrs

1.13

MR

1.13

MR

1.13

 Mister

1.11

Mrs

1.11

Ms

1.00

Activations Density 0.047%

references to individuals identified as "Mr." followed by a name or title

No Comments

No Known Activations