INDEX

Explanations

negations and expressions of uncertainty or doubt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

<bos>

-0.47

comment

-0.38

NOT

-0.37

NOTE

-0.37

 crossorigin

-0.36

ArrowToggle

-0.35

chartInstance

-0.32

 Notwithstanding

-0.32

viz

-0.32

ostante

-0.31

POSITIVE LOGITS

not

1.02

principalColumn

0.70

SBATCH

0.64

########.

0.61

 mitte

0.60

FormTagHelper

0.57

 partly

0.57

 rather

0.56

оргаш

0.55

 Administrativna

0.54

Activations Density 0.588%

negations and expressions of uncertainty or doubt

No Comments

No Known Activations

negations and expressions of uncertainty or doubt

No Comments

No Known Activations